qizhangli

Pinned Repositories

Adversarial-Prompt-Translator
Code for our paper Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation
Language:Python30
Gradient-based-Jailbreak-Attacks
Code for our NeurIPS 2024 paper Improved Generation of Adversarial Examples Against Safety-aligned LLMs
Language:Python4 2 10
ila-plus-plus
Code for our ECCV 2020 paper Yet Another Intermediate-Level Attack.
Language:Python9 2 00
ila-plus-plus-lr
Code for our TPAMI 2022 paper An Intermediate-level Attack Framework on The Basis of Linear Regression.
Language:Python8 1 00
ILPD-attack
Code for our NeurIPS 2023 paper Improving Adversarial Transferability via Intermediate-level Perturbation Decay
Language:Python3 2 00
linbp-attack
Code for our NeurIPS 2020 paper Backpropagating Linearly Improves Transferability of Adversarial Examples.
Language:Python42 1 55
MoreBayesian-attack
Code for our ICLR 2023 paper Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples.
Language:Python18 1 20
nobox-attacks
Code for our NeurIPS 2020 paper Practical No-box Adversarial Attacks against DNNs.
Language:Python33 2 33
ST-AT
Code for our ICLR 2023 paper Squeeze Training for Adversarial Robustness.
Language:Python8 1 11
TA-Bench
Code for our NeurIPS 2023 paper Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly
Language:Python13 2 00

qizhangli's Repositories

qizhangli/linbp-attack
Code for our NeurIPS 2020 paper Backpropagating Linearly Improves Transferability of Adversarial Examples.
Language:Python42 1 55
qizhangli/nobox-attacks
Code for our NeurIPS 2020 paper Practical No-box Adversarial Attacks against DNNs.
Language:Python33 2 33
qizhangli/MoreBayesian-attack
Code for our ICLR 2023 paper Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples.
Language:Python18 1 20
qizhangli/TA-Bench
Code for our NeurIPS 2023 paper Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly
Language:Python13 2 00
qizhangli/ila-plus-plus
Code for our ECCV 2020 paper Yet Another Intermediate-Level Attack.
Language:Python9 2 00
qizhangli/ila-plus-plus-lr
Code for our TPAMI 2022 paper An Intermediate-level Attack Framework on The Basis of Linear Regression.
Language:Python8 1 00
qizhangli/ST-AT
Code for our ICLR 2023 paper Squeeze Training for Adversarial Robustness.
Language:Python8 1 11
qizhangli/Gradient-based-Jailbreak-Attacks
Code for our NeurIPS 2024 paper Improved Generation of Adversarial Examples Against Safety-aligned LLMs
Language:Python4 2 10
qizhangli/Adversarial-Prompt-Translator
Code for our paper Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation
Language:Python30
qizhangli/ILPD-attack
Code for our NeurIPS 2023 paper Improving Adversarial Transferability via Intermediate-level Perturbation Decay
Language:Python3 2 00