arXiv AI By Thomas Winninger, Boussad Addad, Katarzyna Kapusta

Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models

Read the original on arXiv AI →

arXiv:2503. 06269v3 Announce Type: replace-cross Abstract: Traditional white-box methods for creating adversarial perturbations against LLMs typically rely only on gradient computation from the targeted model, ignoring the internal mechanisms responsible for attack success or failure.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI
Jul 9

NonTextual Target Attack

arXiv:2510. 02999v5 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined target responses.

By Xinzhe Huang, Wenjing Hu, Tianhang Zheng, Kedong Xiu, Hongsheng Hu, Xiaojun Jia, Di Wang, Zhan Qin, Kui Ren
Hugging Face Trending Papers
Jul 29

ToxScreen: Detecting Whether an LLM Has Been Poisoned

As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time. We ask whether a defender can recover such a trigger under realistic affordances, namely white-box access to the weights and knowledge of the behavior of concern, but no training data, no trusted reference model, no knowledge of the trigger, and no certainty that the model is poisoned.

arXiv Machine Learning
Jul 30

ToxScreen: Detecting Whether an LLM Has Been Poisoned

arXiv:2607. 26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that covertly manipulate model behavior at inference time.

By Anthony Hughes, Nicole Xing, Collin Francel, Andy Kim, Andrew Draganov