paper-with-me

Papers

Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples

2024-10-21 · Kirill Lukyanov, Andrew Perminov, Denis Turdakov, Mikhail Pautov

The vulnerability of artificial neural networks to adversarial perturbations in the black-box setting is widely studied in the literature. The majority of attack methods to construct these perturbations suffer from an impractically large number of queries required to find an adversarial example. In this work, we focus on knowledge distillation as an approach to conduct transfer-based black-box adversarial attacks and propose an iterative training of the surrogate model on an expanding dataset. This work is the first, to our knowledge, to provide provable guarantees on the success of knowledge distillation-based attack on classification neural networks: we prove that if the student model has enough learning capabilities, the attack on the teacher model is guaranteed to be found within the finite number of distillation iterations.

📄 PDF Abstract BibTeX arXiv:2410.15889

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…
Focus 설명 없음

Similar Papers 제목 키워드 기반

Mutual Information Guided Backdoor Mitigation for Pre-trained Encoders

2024-06-05 · Tingxu Han, Weisong Sun, Ziqi Ding, Chunrong Fang 외

Self-supervised learning (SSL) is increasingly attractive for pre-training encoders without requiring labeled data. Downstream tasks built on top of those pre-trained encoders can achieve nearly state-of-the-art performa…

Knowledge DistillationSelf-Supervised Learning

SELF-KNOWLEDGE DISTILLATION ADVERSARIAL ATTACK

2019-09-25 · Ma Xiaoxiong[1], Wang Renzhi[1], Tian Cong, Dong Zeqian 외

Neural networks show great vulnerability under the threat of adversarial examples. By adding small perturbation to a clean image, neural networks with high classification accuracy can be completely fooled. One intr…

Adversarial AttackKnowledge DistillationSelf-Knowledge Distillation

Pay Attention to the Triggers: Constructing Backdoors That Survive Distillation

2025-10-21 · Giovanni De Muri, Mark Vero, Robin Staab, Martin Vechev arxiv

LLMs are often used by downstream users as teacher models for knowledge distillation, compressing their capabilities into memory-efficient models. However, as these teacher models may stem from untrusted parties, distill…

Knowledge Distillation

Contract And Conquer: How to Provably Compute Adversarial Examples for a Black-Box Model?

2026-03-11 · Anna Chistyakova, Mikhail Pautov arxiv

Black-box adversarial attacks are widely used as tools to test the robustness of deep neural networks against malicious perturbations of input data aimed at a specific change in the output of the model. Such methods, alt…

Knowledge Distillation

Meta-KD: A Meta Knowledge Distillation Framework for Language Model Compression across Domains

2020-12-02 · ACL 2021 5 · Haojie Pan, Chengyu Wang, Minghui Qiu, Yichang Zhang 외

Pre-trained language models have been applied to various NLP tasks with considerable performance gains. However, the large model sizes, together with the long inference time, limit the deployment of such models in real-t…

Knowledge DistillationLanguage ModelingLanguage ModellingMeta-Learning+2