5 papers
Can Large Language Models Reason about Event-Time Stream-Processing Semantics?
Zhuoxi Wang, Shibo Zheng, Haoyu Zhang
Streaming systems increasingly hand work to large language models (LLMs): writing pipelines, triaging alerts, reading logs. All of it assumes the model knows how event-time stream…
Whose Refusal Is It? The Unmeasured Contribution of Black-Box Multimodal Guardrails
Haoyu Zhang, Xiao Luo, Haowen Xu +4
A black-box guardrail is evaluated as though the safety number it earns were its own. It is not. A defended pipeline holds two components that can refuse (the guardrail, and the ta…
Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks
Haoyu Zhang, Xiangchen Guan, Shibo Zheng +2
We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models (VLMs): pairing an encoded jailbreak prompt with an unrela…
Attack Ensembles Expose a Safety-Utility Trade-off in Black-Box Guard Defenses Against Encoded VLM Jailbreaks
Haoyu Zhang, Zhuoxi Wang, Shibo Zheng +7
Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet a guard judges an input's surface form, not its meaning: a harmful request re-encod…
Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses
Haoyu Zhang, Shibo Zheng, Xiangchen Guan +4
A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% defense success rate. We show it…