paper-with-me

Papers

Advancing Generalized Transfer Attack with Initialization Derived Bilevel Optimization and Dynamic Sequence Truncation

2024-06-04 · Yaohua Liu, Jiaxin Gao, Xuan Liu, Xianghao Jiao, Xin Fan, Risheng Liu

Transfer attacks generate significant interest for real-world black-box applications by crafting transferable adversarial examples through surrogate models. Whereas, existing works essentially directly optimize the single-level objective w.r.t. the surrogate model, which always leads to poor interpretability of attack mechanism and limited generalization performance over unknown victim models. In this work, we propose the \textbf{B}il\textbf{E}vel \textbf{T}ransfer \textbf{A}ttac\textbf{K} (BETAK) framework by establishing an initialization derived bilevel optimization paradigm, which explicitly reformulates the nested constraint relationship between the Upper-Level (UL) pseudo-victim attacker and the Lower-Level (LL) surrogate attacker. Algorithmically, we introduce the Hyper Gradient Response (HGR) estimation as an effective feedback for the transferability over pseudo-victim attackers, and propose the Dynamic Sequence Truncation (DST) technique to dynamically adjust the back-propagation path for HGR and reduce computational overhead simultaneously. Meanwhile, we conduct detailed algorithmic analysis and provide convergence guarantee to support non-convexity of the LL surrogate attacker. Extensive evaluations demonstrate substantial improvement of BETAK (e.g., $\mathbf{53.41}$\% increase of attack success rates against IncRes-v$2_{ens}$) against different victims and defense methods in targeted and untargeted attack scenarios. The source code is available at https://github.com/callous-youth/BETAK.

📄 PDF Abstract BibTeX arXiv:2406.02064

Code (1)

callous-youth/betak 공식 구현 pytorch

Tasks

Bilevel Optimization

Similar Papers 제목 키워드 기반

Boosting the Transferability of Adversarial Attacks with Global Momentum Initialization

2022-11-21 · Jiafeng Wang, Zhaoyu Chen, Kaixun Jiang, Dingkang Yang 외

Deep Neural Networks (DNNs) are vulnerable to adversarial examples, which are crafted by adding human-imperceptible perturbations to the benign inputs. Simultaneously, adversarial examples exhibit transferability across …

Jailbreak Attack Initializations as Extractors of Compliance Directions

2025-02-13 · Amit Levi, Rom Himelstein, Yaniv Nemcovsky, Avi Mendelson 외

Safety-aligned LLMs respond to prompts with either compliance or refusal, each corresponding to distinct directions in the model's activation space. Recent works show that initializing attacks via self-transfer from othe…

Renofeation: A Simple Transfer Learning Method for Improved Adversarial Robustness

2020-02-07 · Ting-Wu Chin, Cha Zhang, Diana Marculescu

Fine-tuning through knowledge transfer from a pre-trained model on a large-scale dataset is a widely spread approach to effectively build models on small-scale datasets. In this work, we show that a recent adversarial at…

Adversarial AttackAdversarial RobustnessTransfer Learning

Transferable Adversarial Attacks on SAM and Its Downstream Models

2024-10-26 · Song Xia, Wenhan Yang, Yi Yu, Xun Lin 외

The utilization of large foundational models has a dilemma: while fine-tuning downstream tasks from them holds promise for making use of the well-generalized knowledge in practical applications, their open accessibility …

Adversarial Attack

TREND: Transferability based Robust ENsemble Design

2020-08-04 · Deepak Ravikumar, Sangamesh Kodge, Isha Garg, Kaushik Roy

Deep Learning models hold state-of-the-art performance in many fields, but their vulnerability to adversarial examples poses threat to their ubiquitous deployment in practical settings. Additionally, adversarial inputs g…

Adversarial RobustnessQuantization