This work proposes VaccineBooster, a single alignment procedure that combines embedding perturbation and weight-level gradient attenuation within each training step, and indicates a trade-off: embedding perturbation primarily reduces flagged harmful content, whereas gradient attenuation primarily preserves explicit ref...
M. Akram, Mufid Kamel Marican, Anvesh Reddy Yenugu et al.· 0 citations
These findings show that gradient-based signals can support multi-turn jailbreak detection, but reliable deployment requires calibration on realistic benign conversations, short-window scoring, length-aware thresholds, and evaluation across attack types and model architectures.
Omar Sheta, Rinku Deuja, Hadi Masoudi et al.· 0 citations
Extensive evaluations across three representative vulnerability cases and ten backdoor attacks, along with sixteen competitive baselines, demonstrate that CodeTracer consistently achieves high forensic accuracy, low false identification rates, and strong robustness against adaptive attacks.
Anjun Gao, Yueyang Quan, Zhuqing Liu et al.· arXiv.org· 2 citations
A fine-tuning-stage defense that simultaneously hardens LLMs against both attack classes by redistributing safety signals across a broader set of neurons, and provides a formal guarantee that NeuronGuard strictly reduces the attack success rate (ASR) upper bound.
Anjun Gao, Yueyang Quan, Yu Xia et al.· 2 citations
It is proved that, under an honest-majority assumption and a representation-level separation condition, RAGSentinel exactly recovers a poison-free majority-sized context.
Yueyang Quan, Anjun Gao, Yu Xia et al.· 0 citations
Experimental results show that AgentLocate consistently outperforms existing failure localization methods in identifying both responsible agents and failure steps, while remaining efficient in terms of token usage and running time.
Yu Xia, Anjun Gao, Yueyang Quan et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
