From the 2 of 8 linked papers with an AI index.
8 papers
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…
Borrowed Strength: Best-of-N Search over a Code EncodingBreaks Self-Check Jailbreak Defenses
Haoyu Zhang, Shibo Zheng, Xiangchen Guan +4
The paper demonstrates that a self‑check defense (SAGE) for language models can be bypassed by combining a code‑completion encoding attack with a best‑of‑N search, dramatically inc…
Attack Ensembles Expose a Safety-Utility Trade-off in Black-Box Guard Defenses Against Encoded VLM Jailbreaks
Haoyu Zhang, Zhuoxi Wang, Shibo Zheng +7
The paper proposes a guard‑agnostic recovery‑and‑decode module that transcribes encoded or visual text into plain language before applying existing safety classifiers for vision‑la…
Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis
Haoyu Zhang, Mohammad Zandsalimy, Shanu Sushmita
Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prom…
Temporal Flattening in LLM-Generated Text: Comparing Human and LLM Writing Trajectories
Zhanwei Cao, YeoJin Go, Yifan Hu +1
Large language models (LLMs) are increasingly used in daily applications, from content generation to code writing, where each interaction treats the model as stateless, generating…