jailbreak attacks 2adversarial evaluation 1adversarial prompting 1best-of-N search 1code encoding 1model safety 1recovery decoding 1safety guards 1self-check defense 1vision-language models 1
From the 2 of 2 linked papers with an AI index.
2 papers
cs.CR2026
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…
cs.CR2026
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…