From dd00fda4ee8a902d3f9b2875e4f128533352575e Mon Sep 17 00:00:00 2001 From: Marco Rosa Date: Mon, 12 Feb 2024 11:30:53 +0100 Subject: [PATCH 1/2] Fix typo in faster-alzantot --- README.md | 2 +- README_ZH.md | 2 +- docs/1start/attacks4Components.md | 2 +- docs/1start/what_is_an_adversarial_attack.md | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) diff --git a/README.md b/README.md index c05e20263..99cd455e9 100644 --- a/README.md +++ b/README.md @@ -186,7 +186,7 @@ To run an attack recipe: `textattack attack --recipe [recipe_name]` Greedy replace-1 scoring and multi-transformation character-swap attack (["Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers" (Gao et al., 2018)](https://arxiv.org/abs/1801.04354) - fast-alzantot + faster-alzantot Untargeted {Classification, Entailment} Percentage of words perturbed, Language Model perplexity, Word embedding distance Counter-fitted word embedding swap diff --git a/README_ZH.md b/README_ZH.md index c9bcf944a..4462f61d9 100644 --- a/README_ZH.md +++ b/README_ZH.md @@ -168,7 +168,7 @@ textattack attack --model lstm-mr --num-examples 20 \ 贪心搜索 replace-1 分数，多种变换的字符交换式的攻击 (["Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers" (Gao et al., 2018)](https://arxiv.org/abs/1801.04354) - fast-alzantot + faster-alzantot 无目标
{分类，蕴含} 被扰动词的比例，语言模型的困惑度，词嵌入的距离 Counter-fitted 词嵌入替换 diff --git a/docs/1start/attacks4Components.md b/docs/1start/attacks4Components.md index 54030650b..3350dafaf 100644 --- a/docs/1start/attacks4Components.md +++ b/docs/1start/attacks4Components.md @@ -123,7 +123,7 @@ A `SearchMethod` takes as input an initial `GoalFunctionResult` and returns a fi Greedy replace-1 scoring and multi-transformation character-swap attack (["Black-box Generation of Adversarial Text Sequences to Evade Deep Learning Classifiers" (Gao et al., 2018)](https://arxiv.org/abs/1801.04354) - fast-alzantot + faster-alzantot Untargeted {Classification, Entailment} Percentage of words perturbed, Language Model perplexity, Word embedding distance Counter-fitted word embedding swap diff --git a/docs/1start/what_is_an_adversarial_attack.md b/docs/1start/what_is_an_adversarial_attack.md index f9a2c5fec..975af4dce 100644 --- a/docs/1start/what_is_an_adversarial_attack.md +++ b/docs/1start/what_is_an_adversarial_attack.md @@ -70,7 +70,7 @@ TextAttack attack recipes that fall under this category: deepwordbug, hotflip, p Some NLP models are trained to measure semantic similarity. Adversarial attacks based on the notion of semantic indistinguishability typically use another NLP model to enforce that perturbations are grammatically valid and semantically similar to the original input. -TextAttack attack recipes that fall under this category: alzantot, bae, bert-attack, fast-alzantot, iga, kuleshov, pso, pwws, textbugger\*, textfooler +TextAttack attack recipes that fall under this category: alzantot, bae, bert-attack, faster-alzantot, iga, kuleshov, pso, pwws, textbugger\*, textfooler \*The textbugger attack generates perturbations using both typo-like character edits and synonym substitutions. It could be considered to use both definitions of indistinguishability. From 373fdf5d335bc4d46cf21fa8efee00ed1ff0e0b6 Mon Sep 17 00:00:00 2001 From: Marco Rosa Date: Mon, 12 Feb 2024 11:32:39 +0100 Subject: [PATCH 2/2] Fix typo in recipe name --- textattack/attack_recipes/genetic_algorithm_alzantot_2018.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/textattack/attack_recipes/genetic_algorithm_alzantot_2018.py b/textattack/attack_recipes/genetic_algorithm_alzantot_2018.py index 2c42c6ebf..2fbacd06d 100644 --- a/textattack/attack_recipes/genetic_algorithm_alzantot_2018.py +++ b/textattack/attack_recipes/genetic_algorithm_alzantot_2018.py @@ -5,7 +5,7 @@ (Generating Natural Language Adversarial Examples) .. warning:: - This attack uses a very slow language model. Consider using the ``fast-alzantot`` + This attack uses a very slow language model. Consider using the ``faster-alzantot`` recipe instead. """