Federated fine-tuning of large language models (LLMs) allows multiple clients to collaboratively adapt models without sharing raw data, offering strong privacy benefits. However, this setting is highly vulnerable to backdoor attacks, in which malicious clients manipulate their updates to induce targeted behaviors while...
Xi Chen, Chun-Yi Zhou, Rui Zeng et al.· 0 citations
This work proposes ReGap, a data-free attack that recovers private associations using task structure, filters them by answer-token likelihood, and updates the target model via low-rank adaptation, which requires neither target answers nor auxiliary genuine private supervision.
Jian-Hong Li, Jia-Hao Chen, Yuwen Pu et al.· 0 citations
SAVER is introduced, a transition-centered framework in which Substrate locates reusable influence, Adaptation captures how it changes, Violation identifies compromised safety attributes, Exposure marks where failures become observable, and Response assesses containment, repair, or revocation.
Jia-Hao Chen, Zhou Feng, Ou-Bo Ma et al.· 1 citation
Deep Reinforcement Learning (DRL) has demonstrated remarkable capabilities in domains such as robotics, finance, and autonomous systems. With the increasing cost of training, DRL models are increasingly shared and reused via model marketplaces, cloud platforms, and open-source repositories. This trend exposes DRL syste...
Ou-Bo Ma, L. Du, Yang Dai et al.· IEEE Transactions on Informa...· 0 citations
This work presents a unified comparison of large language models, AI agents, and embodied agents, introducing a taxonomy of risks spanning data, models, systems, content, and applications, alongside a catalog of 24 specific threats.
Existing Federated Learning (FL) backdoor attacks commonly employ round-wise proximity strategies, dynamically adapting malicious updates to mimic benign ones in order to evade detection. However, such adaptive mechanisms often introduce instability, increase computational overhead, and create temporal patterns that ma...
Xi Chen, Rui Zeng, Chun-Yi Zhou et al.· IEEE Transactions on Informa...· 0 citations
SkillShift is presented, a constrained black-box framework for covert policy steering without explicit target command injection or task hijacking that combines semantically plausible policy edits with hierarchical validation, failure-guided optimization, and strategy compression to preserve effectiveness, output validi...
Jia-Rui Li, Jia-Hao Chen, Chun-Yi Zhou et al.· 0 citations
This work forms this problem as backdoor generalization under training--inference trigger shift and introduces Lilith, a black-box anchor-to-family framework that achieves high family-wise attack success with limited utility degradation and a small trigger generalization gap.
Unsafe Semantic Distillation is proposed, which aligns adversarial perturbations with distributional representations of unsafe content rather than prompt-specific instances, and achieves 84% attack success rates, outperforming existing methods and exposing fundamental vulnerabilities in current multimodal safety archit...
Shuo Shi, Ruiping Yin, Na-En Xu et al.· Proceedings of the 32nd ACM...· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
