Meta tags:

Headings (most frequently used words):

textattack, documentation,

Text of the page (most frequently used words):
#textattack (152), attack (111), package (78), class (64), models (63), trainingargs (60), attackargs (54), submodules (51), adversarial (49), word (44), model (43), trainer (38), extra_repr_keys (38), for (36), custom (36), nlp (36), our (36), attackedtext (33), augmenterargs (30), with (29), dataset (29), constraints (29), the (28), swap (28), search (28), examples (28), recipes (28), attacks (28), build (26), attacking (26), tutorial (26), training (25), attacker (24), goalfunction (24), and (23), constraint (23), attackresult (23), subpackages (21), results (21), goal (21), recipe (20), transformation (20), augmentation (18), github (18), benchmarking (18), bert (17), searchmethod (17), particleswarmoptimization (17), greedywordswapwir (17), differentialevolution (17), is_black_box (16), perform_search (16), function (16), attacklogmanager (16), metrics (15), transformations (15), from (15), datasetargs (14), beamsearch (14), augmenter (14), conclusion (14), creating (14), details (14), check_transformation_compatibility (13), algorithm (13), datasets (13), text (12), huggingfacedataset (12), skippedattackresult (12), failedattackresult (12), how (12), more (12), base (12), via (12), using (11), attackcheckpoint (11), classification (11), pretransformationconstraint (11), run (11), train (10), modelargs (10), genetic (10), available (10), use (10), paper (10), functions (9), method (9), generating (9), visdomlogger (9), file (9), register_subcommand (9), str_lines (9), goal_function_result_str (9), wordembedding (8), improvedgeneticalgorithm (8), greedysearch (8), trained (8), logger (8), attackrecipe (8), a2t (8), api (8), multilingual (8), new (8), evaluation (8), title (8), reevaluating (8), help (8), random_seed (7), embedding (7), shared (7), data (7), language (7), wrapper (7), user (7), minimizebleu (7), maximizelevenshtein (7), targetedclassification (7), inputreduction (7), input (7), classificationgoalfunction (7), evaluate (6), gensimwordembedding (6), abstractwordembedding (6), methods (6), quality (6), log_summary_rows (6), logs (6), flush (6), filelogger (6), loggers (6), namedentityrecognition (6), check_compatibility (6), modification (6), evalmodelcommand (6), commands (6), augment (6), successfulattackresult (6), maximizedattackresult (6), robust (6), alzantot (6), bae (6), guide (6), this (6), transformers (6), you (6), components (6), talk (6), citations (6), code (6), towards (6), improving (6), algorithms (6), command (6), usage (6), words (5), abstract (5), geneticalgorithm (5), alzantotgeneticalgorithm (5), natural (5), tensorflow (5), huggingface (5), pre (5), metric (5), log_attack_result (5), summary (5), texttotextgoalfunction (5), nonoverlappingoutput (5), goal_functions (5), targetedstrict (5), targetedbonus (5), bonus (5), logitsum (5), untargetedclassification (5), determine (5), texttotextgoalfunctionresult (5), goalfunctionresultstatus (5), searching (5), goalfunctionresult (5), classificationgoalfunctionresult (5), result (5), listthingscommand (5), modelevalargs (5), pruthi2019 (5), recognition (5), kuleshov2017 (5), chinese (5), checklist (5), parallel (4), output_dir (4), log_to_wandb (4), commandlinetrainingargs (4), training_step (4), get_train_dataloader (4), get_optimizer_and_scheduler (4), get_eval_dataloader (4), evaluate_step (4), update_attack_args (4), from_checkpoint (4), attack_dataset (4), shuffle (4), create_loggers_from_args (4), get_transformations (4), get_indices_to_order (4), filter_transformations (4), cuda_ (4), cpu_ (4), character (4), misc (4), populationmember (4), score (4), based (4), particle (4), swarm (4), optimization (4), helpers (4), calculate (4), weightsandbiaseslogger (4), log_sep (4), close (4), jsonsummarylogger (4), csvlogger (4), seq2sick (4), successful (4), reduction (4), max (4), grammaticality (4), trainmodelcommand (4), main (4), peekdatasetcommand (4), benchmarkrecipecommand (4), augmentcommand (4), attackresumecommand (4), attackcommand (4), attack_results (4), reference (4), __len__ (4), __getitem__ (4), notebook (4), keras (4), first (4), list (4), named (4), entity (4), nltk (4), end (4), eval (4), contributing (4), start (4), want (4), feature (4), contribute (4), slack (4), generated (4), defined (4), supports (4), extended (4), design (4), https (4), some (4), set (4), sota (4), reevaluation (4), four (4), have (4), implemented (4), analysis (4), what (4), type (4), cased (4), distilbert (4), uncased (4), line (4), commandline (4), sequence (4), papers (4), other (4), questions (4), where (4), faq (4), features (4), installation (4), install (4), documentation (4), built (3), 2021 (3), qdata (3), num_examples_offset (3), num_examples (3), clear_cache (3), compositetransformation (3), composite (3), invisible (3), random (3), recover_word_case (3), changing (3), word_swaps (3), word2index (3), nearest_neighbours (3), index2word (3), get_mse_dist (3), get_cos_sim (3), embeddings (3), checkpoints (3), scikit (3), learn (3), wrappers (3), lstm (3), usemetric (3), init_attack_example (3), get_results (3), get_result (3), get_output (3), bleu (3), case (3), targeted (3), has (3), been (3), get_text_color_perturbed (3), get_text_color_input (3), get_colored_output (3), goal_function_results (3), call_many (3), textattackcommand (3), cli (3), perturbed_text (3), original_text (3), diff_color (3), textfooler (3), really (3), textbugger (3), pwws (3), combating (3), morpheus2020 (3), improved (3), hotflip (3), faster (3), deepwordbug (3), clare (3), imperceptible (3), perturbations (3), source (3), default_output_dir (2), weight_decay (2), wandb_project (2), tb_log_dir (2), save_last (2), query_budget_train (2), per_device_train_batch_size (2), per_device_eval_batch_size (2), num_warmup_steps (2), num_train_adv_examples (2), num_epochs (2), num_clean_epochs (2), logging_interval_step (2), log_to_tb (2), load_best_model_at_end (2), learning_rate (2), gradient_accumulation_steps (2), early_stopping_epochs (2), checkpoint_interval_steps (2), checkpoint_interval_epochs (2), attack_num_workers_per_device (2), attack_epoch_interval (2), alpha (2), model_from_huggingface (2), model_from_file (2), filter_by_labels (2), dataset_split (2), dataset_from_huggingface (2), dataset_from_file (2), dataset_by_model (2), transformations_per_example (2), pct_words_to_swap (2), overwrite (2), output_csv (2), interactive (2), input_csv (2), input_column (2), high_yield (2), fast_augment (2), exclude_original (2), enable_advanced_metrics (2), set_env_variables (2), pytorch_multiprocessing_workaround (2), attack_from_queue (2), attack_interactive (2), commandlineattackargs (2), silent (2), query_budget (2), num_workers_per_device (2), num_successful_examples (2), log_to_visdom (2), log_to_txt (2), log_to_csv (2), log_summary_to_json (2), enable_advance_metrics (2), disable_stdout (2), csv_coloring_style (2), checkpoint_interval (2), checkpoint_dir (2), attack_n (2), wordinnerswaprandom (2), deterministic (2), swapping (2), deletion (2), characters (2), idx_to_words (2), wordmergemaskedlm (2), word_merges (2), wordinsertionrandomsynonym (2), wordinsertionmaskedlm (2), wordinsertion (2), word_insertions (2), sentencetransformation (2), backtranslation (2), backtranscription (2), sentence_transformations (2), num_words (2), reimplementation (2), greedy (2), search_methods (2), prompt (2), prompt_augmentation (2), modelwrapper (2), tokenizer (2), glove (2), tokenizers (2), advancedattackmetric (2), perplexity (2), meteormetric (2), bertscoremetric (2), attacksuccessrate (2), attackqueries (2), attack_metrics (2), advanced (2), evaluting (2), augmented (2), log_hist (2), track (2), visualize (2), export (2), large (2), llms (2), label (2), targetedstrictgoalfunctionresult (2), targetedbonusgoalfunctionresult (2), logitsumgoalfunctionresult (2), filter_by_labels_ (2), distance (2), semantics (2), rate (2), meteor (2), chrf (2), overlap (2), languagetool (2), cola (2), easydataaugmenter (2), augmentationresult (2), textfoolerjin2019 (2), textbuggerli2018 (2), spanishrecipe (2), seq2sickcheng2018blackbox (2), pwwsren2019 (2), psozang2020 (2), morpheustan2020 (2), inputreductionfeng2018 (2), igawang2019 (2), hotflipebrahimi2017 (2), geneticalgorithmalzantot2018 (2), frenchrecipe (2), fastergeneticalgorithmjia2019 (2), deepwordbuggao2018 (2), clare2020 (2), chineserecipe (2), checklist2020 (2), bertattackli2020 (2), baegarg2019 (2), badcharacters2021 (2), a2tyoo2021 (2), attack_recipes (2), full (2), tutorial11 (2), tutorial10 (2), explaining (2), captum (2), runs (2), allennlp (2), importing (2), testing (2), namedentityconstraint (2), putting (2), all (2), together (2), getting (2), labels (2), sentence (2), caching (2), functools (2), lru_cache (2), ner (2), example (2), classes (2), samples (2), visualizing (2), banana (2), tutorials (2), was (2), heavily (2), inspired (2), awesome (2), tests (2), pull (2), requests (2), component (2), something (2), else (2), add (2), your (2), found (2), bug (2), submitting (2), issue (2), request (2), ways (2), channel (2), can (2), visulizing (2), inputs (2), multiple (2), types (2), besides (2), flowchart (2), tips (2), challenges (2), 2020 (2), jack (2), morris (2), presentations (2), lessons (2), learned (2), designing (2), video (2), recording (2), underline (2), events (2), 192 (2), sessions (2), 7928 (2), lecture (2), 38377 (2), making (2), vanilla (2), feasible (2), robustness (2), two (2), contraints (2), comparing (2), used (2), past (2), venue (2), expanding (2), scope (2), adapting (2), english (2), defense (2), benchmark (2), com (2), framework (2), cite (2), future (2), terminology (2), fine (2), tuned (2), target (2), task (2), output (2), paperswithcode (2), card (2), each (2), xlnet (2), roberta (2), albert (2), wordcnn (2), zoo (2), interface (2), augmenting (2), general (2), recipe_name (2), running (2), too (2), slow (2), create (2), loading (2), mechanism (2), see (2), here (2), many (2), dependent (2), library (2), issues (2), following (2), could (2), try (2), concrete (2), readthedocs (2), apis (2), ask (2), quick (2), examining (2), peek (2), listing (2), resume (2), evaluating (2), optional (2), dependencies (2), pip (2), should (2), basic (2), introduction (2), get (2), started (2), provided, read, docs, theme, sphinx, copyright, uva, lab, next, order, worddeletion, wordswapwordnet, synonyms, wordnet, wordswapreorderings, reorderings, wordswaprandomcharactersubstitution, substitution, wordswaprandomcharacterinsertion, insertion, wordswaprandomcharacterdeletion, wordswapqwerty, swaps, qwerty, adjacent, keys, wordswapneighboringcharacterswap, neighboring, wordswapmaskedlm, masked, wordswapinvisiblecharacters, wordswapinflections, inflections, wordswaphownet, openhownet, wordswaphomoglyphswap, homoglyph, wordswapgradientbased, gradient, wordswapextend, extension, wordswapembedding, wordswapdifferentialevolution, differential, evolution, wordswapdeletions, deletions, wordswapcontract, contraction, wordswapchangenumber, number, wordswapchangename, name, wordswapchangelocation, location, wordswap, chn_transformations, find_merge_index, wordmerge, merge, check_if_one_word, path, counterfitted_glove_embedding, loads, related, distances, validate_model_gradient_word_swap_compatibility, validate_model_goal_function_compatibility, transformation_consists_of_word_swaps_differential_evolution, transformation_consists_of_word_swaps_and_deletions, transformation_consists_of_word_swaps, transformation_consists_of, validators, fields, results_count, num_successful_attacks, num_skipped_attacks, num_remaining_attacks, num_maximized_attacks, num_failed_attacks, datetime, dataset_offset, save, load, words_per_input, tokenizer_input, newly_swapped_words, column_labels, split_token, words_diff_ratio, words_diff_num, text_window_around_index, text_until_word_index, text_after_word_index, replace_words_at_indices, replace_word_at_index, printable_text, pos_of_word_index, ner_of_word_index, ith_word_diff, insert_text_before_word_index, insert_text_after_word_index, get_deletion_indices, generate_new_attacked_text, free_memory, first_word_diff_index, first_word_diff, delete_word_at_index, convert_from_original_idxs, all_words_diff, align_with_model_tokens, attacked, batch_model_predict, zip_stanza_result, zip_flair_result, words_from_text, strip_bpe_artifacts, process_label_name, is_one_word, has_letter, flair_tag, default_class_repr, color_text, color_from_output, color_from_label, check_if_subword, check_if_punctuations, add_indent, textattackflairtokenizer, reprmixin, ansi_escape_codes, sigmoid, set_seed, load_textattack_model_from_path, html_table_from_rows, html_style_from_dict, hashable, get_textattack_model_num_labels, unzip_file, set_cache_dir, s3_url, path_in_cache, http_get, download_from_url, download_from_s3, load_module_from_file, lazyloader, utils, get_victim_model, populationbasedsearch, population, normalize, xiaosen, wang, hao, jin, kun, 2019, importance, ranking, beam, promptaugmentationpipeline, tensorflowmodelwrapper, sklearnmodelwrapper, pytorchmodelwrapper, pytorch, huggingfacemodelwrapper, t5tokenizer, wordleveltokenizer, glovetokenizer, wordcnnforclassification, cnntextlayer, cnn, load_cached_state_dict, util, t5fortexttotext, generate, lstmforclassification, gloveembeddinglayer, embeddinglayer, moderl, specified, sbertmetric, quality_metrics, wordsperturbed, perturbed, wandb, port_is_open, table, hist, bar, visdom, json, csv, log_summary, log_results, log_result, log_attack_details, enable_wandb, enable_visdom, enable_stdout, disable_color, add_output_summary_json, add_output_file, add_output_csv, managing, huggingfacellmwrapper, chatgptwrapper, texttotext, word_difference_score, get_words_cached, get_bleu, attempts, minimize, strict, logit, sum, untargeted, maintaining, same, predicted, hardlabelclassification, hard, classficiation, fucntion, succeeded, skipped, maximizing, namedentityrecognitiongoalfunctionresult, namedentityrecognitionoalfunctionresult, get_datasets_dataset_columns, tedmultitranslationdataset, ted, multi, translationdataset, wordembeddingdistance, bertscore, sentence_encoders, semantic, unmodifablephrases, unmodifiableindices, stopwordmodification, stopword, repeatmodification, repeat, minwordlength, min, lenth, maxwordindexmodification, index, maxnumwordsmodified, maxmodificationrate, inputcolumnmodification, column, pre_transformation, maxwordsperturbed, perturb, levenshteineditdistance, edit, partofspeech, part, speech, grammar, checker, language_models, things, batch_size, test_model_on_dataset, get_preds, wordnetaugmenter, synonyminsertionaugmenter, swapaugmenter, embeddingaugmenter, deletionaugmenter, checklistaugmenter, charswapaugmenter, clareaugmenter, backtranslationaugmenter, backtranscriptionaugmenter, augment_text_with_ids, augment_many, tempresult, spanish, french, view, page,

Text of the page (random words):
transformation_compatibility particleswarmoptimization extra_repr_keys particleswarmoptimization perform_search particleswarmoptimization is_black_box differentialevolution differentialevolution differentialevolution check_transformation_compatibility differentialevolution extra_repr_keys differentialevolution perform_search differentialevolution is_black_box full reference textattack package subpackages textattack attack_recipes package attack recipes package submodules textattack attack_results package textattack attack_results package submodules textattack augmentation package textattack augmentation package submodules textattack commands package textattack commands package submodules textattack constraints package constraints subpackages submodules textattack datasets package datasets package subpackages submodules textattack goal_function_results package goal function result package subpackages submodules textattack goal_functions package goal functions subpackages submodules textattack llms package large language models submodules textattack loggers package misc loggers loggers track visualize and export attack results submodules textattack metrics package metrics package to calculate advanced metrics for evaluting attacks and augmented text subpackages submodules textattack models package models subpackages textattack prompt_augmentation package prompt augmentation submodules textattack search_methods package search methods submodules textattack shared package shared textattack functions subpackages submodules textattack transformations package transformations subpackages submodules submodules attack class attack attack attack attack clear_cache attack cpu_ attack cuda_ attack filter_transformations attack get_indices_to_order attack get_transformations attackargs class attackargs attackargs create_loggers_from_args attackargs attack_n attackargs checkpoint_dir attackargs checkpoint_interval attackargs csv_coloring_style attackargs disable_stdout attackargs enable_advance_metrics attackargs log_summary_to_json attackargs log_to_csv attackargs log_to_txt attackargs log_to_visdom attackargs log_to_wandb attackargs metrics attackargs num_examples attackargs num_examples_offset attackargs num_successful_examples attackargs num_workers_per_device attackargs parallel attackargs query_budget attackargs random_seed attackargs shuffle attackargs silent commandlineattackargs attacker class attacker attacker attack_dataset attacker attack_interactive attacker from_checkpoint attacker update_attack_args attack_from_queue pytorch_multiprocessing_workaround set_env_variables augmenterargs class augmenterargs augmenterargs enable_advanced_metrics augmenterargs exclude_original augmenterargs fast_augment augmenterargs high_yield augmenterargs input_column augmenterargs input_csv augmenterargs interactive augmenterargs output_csv augmenterargs overwrite augmenterargs pct_words_to_swap augmenterargs random_seed augmenterargs recipe augmenterargs transformations_per_example datasetargs class datasetargs datasetargs dataset_by_model datasetargs dataset_from_file datasetargs dataset_from_huggingface datasetargs dataset_split datasetargs filter_by_labels modelargs class modelargs modelargs model modelargs model_from_file modelargs model_from_huggingface trainer class trainer trainer evaluate trainer evaluate_step trainer get_eval_dataloader trainer get_optimizer_and_scheduler trainer get_train_dataloader trainer train trainer training_step trainingargs class commandlinetrainingargs commandlinetrainingargs output_dir trainingargs trainingargs alpha trainingargs attack_epoch_interval trainingargs attack_num_workers_per_device trainingargs checkpoint_interval_epochs trainingargs checkpoint_interval_steps trainingargs early_stopping_epochs trainingargs gradient_accumulation_steps trainingargs learning_rate trainingargs load_best_model_at_end trainingargs log_to_tb trainingargs log_to_wandb trainingargs logging_interval_step trainingargs num_clean_epochs trainingargs num_epochs trainingargs num_train_adv_examples trainingargs num_warmup_steps trainingargs output_dir trainingargs parallel trainingargs per_device_eval_batch_size trainingargs per_device_train_batch_size trainingargs query_budget_train trainingargs random_seed trainingargs save_last trainingargs tb_log_dir trainingargs wandb_project trainingargs weight_decay default_output_dir textattack textattack documentation view page source textattack documentation get started basic introduction what is textattack where should i start nlp attacks data augmentation features installation install with pip install from source optional dependencies faq on installation command line usage data augmentation with textattack augment adversarial attacks with textattack attack training models with textattack train available models textattack models transformers models evaluating models with textattack eval model other commands checkpoints and textattack attack resume listing features with textattack list examining datasets with textattack peek dataset quick api usage attacking a bert model faq via slack where to ask questions via cli help via our papers more details on results via readthedocs more details on apis more concrete questions 0 for many of the dependent library issues the following command is the first you could try 1 how to train 2 use custom models model from a file 3 use custom datasets from a file dataset loading via other mechanism see more details at here custom dataset via attackedtext class 4 benchmarking attacks 5 create custom or new attacks 6 the attacking is too slow recipes attack recipes commandline use help textattack help running attacks textattack attack help attacks and papers implemented attack recipes textattack attack recipe recipe_name recipe usage examples attack recipes api attacks on classification models a2t a2t attack for adversarial training recipe alzantot genetic algorithm faster alzantot genetic algorithm bae bae bert based adversarial examples bert attack checklist deepwordbug hotflip improved genetic algorithm input reduction kuleshov2017 particle swarm optimization pwws textfooler is bert really robust textbugger clare recipe pruthi2019 combating with robust word recognition attacks on sequence to sequence models morpheus2020 seq2sick general imperceptible perturbations algorithm augmenter recipes commandline use augmenting text textattack augment augmentation command line interface augmenter recipes api augmenter recipes textattack model zoo available models textattack models transformers models evaluation results of available models lstm wordcnn albert base v2 bert base uncased distilbert base cased distilbert base uncased roberta base xlnet base cased how we have trained the textattack models training details for each textattack model more details on textattack fine tuned nlp models details on target nlp task input type output type sota results on paperswithcode model card on huggingface using textattack what is an adversarial attack in nlp terminology adversarial examples in nlp generating adversarial examples with textattack the future of adversarial attacks in nlp how to cite textattack main paper textattack a framework for adversarial attacks data augmentation and adversarial training in nlp our github on textattack https github com qdata textattack our analysis paper reevaluating adversarial examples in natural language our github on reevaluation reevaluating nlp adversarial examples github our analysis paper searching for a search method benchmarking search algorithms for generating nlp adversarial examples our github on benchmarking textattack search benchmark github our defense paper title towards improving adversarial training of nlp models code is available citations our extended use case paper expanding scope adapting english adversarial attacks to chinese abstract venue tutorial code citations four components of textattack attacks goal functions constraints transformations search methods on benchmarking attack recipes four components in attack recipes we have implemented benchmarking search algorithms for generating nlp adversarial examples title searching for a search method benchmarking search algorithms for generating nlp adversarial examples our search benchmarking result github our benchmarking results on comparing search methods used in the past attacks benchmarking attack recipes on quality of generated adversarial examples and how to set attack contraints title reevaluating adversarial examples in natural language our github on reevaluation reevaluating nlp adversarial examples github some of our evaluation results on quality of two sota attack recipes some of our evaluation results on how to set constraints to evaluate nlp model s adversarial robustness making vanilla adversarial training of nlp models feasible title towards improving adversarial training of nlp models video recording of this talk https underline io events 192 sessions 7928 lecture 38377 towards improving adversarial training of nlp models code is available citations a2t attack recipe lessons learned in designing textattack presentations on textattack 2020 jack morris summary tutorial talk on textattack 2021 dr qi s summary tutorial talk on textattack challenges in design our design tips textattack flowchart more details in reference textattack extended functions multilingual textattack supports multiple model types besides huggingface models and our textattack models multilingual supports user defined custom inputs and models custom datasets dataset from a file custom model from a file user defined custom attack components visulizing textattack generated examples how can i contribute to textattack slack channel ways to contribute submitting a new issue or feature request found a bug do you want to add your model do you want a new feature a component a recipe or something else start contributing pull requests checklist tests this guide was heavily inspired by the awesome transformers guide to contributing notebook tutorials tutorial 0 textattack end to end train eval attack training evaluation attack conclusion bonus tutorial 1 transformations goal function search method transformation constraints a custom transformation banana word swap using our transformation creating the goal function model and dataset creating the attack using the attack visualizing attack results conclusion bonus attacking custom samples tutorial 2 constraints classes of constraints a new constraint a custom constraint nltk and named entity recognition nltk ner example caching with functools lru_cache putting it all together getting a list of named entity labels from a sentence creating our namedentityconstraint testing our constraint conclusion tutorial 3 augmentation creating an augmenter pre built augmentation recipes conclusion tutorial 4 custom word embeddings importing the model creating a custom dataset creating an attack attack results with custom dataset creating a custom word embedding attack results with custom dataset and word embedding tutorial 5 attacking tensorflow models run textattack on a trained tensorflow model first training attacking conclusion tutorial 6 attacking scikit learn models training attacking conclusion tutorial 7 attacking allennlp models tutorial 8 attacking keras models this notebook runs textattack on a trained keras model training attacking conclusion tutorial 9 attacking multilingual models tutorial10 explaining attacking bert model using captum tutorial11 attacking multilingual chinese nlp model using textattack api user guide attack attack attack attack attack attack cpu_ attack cuda_ attack filter_transformations attack get_indices_to_order attack get_transformations attackrecipe attackrecipe attackrecipe build attacker attacker attacker attacker attack_dataset attacker from_checkpoint attacker update_attack_args attackargs attackargs attackargs create_loggers_from_args attackresult attackresult attackresult attackresult diff_color attackresult goal_function_result_str attackresult original_text attackresult perturbed_text attackresult str_lines successfulattackresult successfulattackresult failedattackresult failedattackresult failedattackresult goal_function_result_str failedattackresult str_lines skippedattackresult skippedattackresult skippedattackresult goal_function_result_str skippedattackresult str_lines maximizedattackresult maximizedattackresult trainer trainer trainer trainer evaluate trainer evaluate_step trainer get_eval_dataloader trainer get_optimizer_and_scheduler trainer get_train_dataloader trainer train trainer training_step trainingargs trainingargs datasets dataset dataset dataset __getitem__ dataset __len__ huggingfacedataset huggingfacedataset huggingfacedataset __getitem__ huggingfacedataset __len__ goalfunction goalfunction goalfunction goalfunction extra_repr_keys goalfunction get_output goalfunction get_result goalfunction get_results goalfunction init_attack_example logitsum logitsum namedentityrecognition namedentityrecognition targetedstrict targetedstrict targetedbonus targetedbonus classificationgoalfunction classificationgoalfunction classificationgoalfunction extra_repr_keys targetedclassification targetedclassification targetedclassification extra_repr_keys untargetedclassification untargetedclassification inputreduction inputreduction inputreduction extra_repr_keys texttotextgoalfunction texttotextgoalfunction minimizebleu minimizebleu minimizebleu extra_repr_keys nonoverlappingoutput nonoverlappingoutput maximizelevenshtein maximizelevenshtein maximizelevenshtein extra_repr_keys constraints constraint constraint constraint call_many constraint check_compatibility constraint extra_repr_keys pretransformationconstraint pretransformationconstraint pretransformationconstraint check_compatibility pretransformationconstraint extra_repr_keys transformations transformation transformation composite transformation compositetransformation searchmethod searchmethod searchmethod searchmethod check_transformation_compatibility searchmethod perform_search searchmethod is_black_box beamsearch beamsearch beamsearch extra_repr_keys beamsearch perform_search beamsearch is_black_box greedysearch greedysearch greedysearch extra_repr_keys greedywordswapwir greedywordswapwir greedywordswapwir check_transformation_compatibility greedywordswapwir extra_repr_keys greedywordswapwir perform_search greedywordswapwir is_black_box alzantotgeneticalgorithm alzantotgeneticalgorithm improvedgeneticalgorithm improvedgeneticalgorithm improvedgeneticalgorithm extra_repr_keys particleswarmoptimization particleswarmoptimization particleswarmoptimization check_transformation_compatibility particleswarmoptimization extra_repr_keys particleswarmoptimization perform_search particleswarmoptimization is_black_box differentialevolution differentialevolution differentialevolution check_transformation_compatibility differentialevolution extra_repr_keys d...