Li Wang

The paper introduces EvoJail, an automated multi-objective evolutionary framework that systematically discovers diverse and effective long-tail jailbreak attacks against LLMs by optimizing for attack effectiveness and minimizing output perplexity.

The paper proposes TriageFuzz, a token-aware fuzzing framework that significantly reduces the number of queries needed to jailbreak LLMs while maintaining high attack success rates.

This paper systematically measures and explains how sequential model defenses can conflict, finding that 38.9% of ordered defense sequences cause measurable risk exacerbation due to anti-aligned parameter updates in shared layers.

ZipRL introduces an adaptive context compression framework that significantly improves the performance and efficiency of LLMs in complex, multi-turn agent tasks by combining multi-granularity compression with Hindsight Response Replay.

The paper introduces ODYSSEY, a confidential blockchain that mitigates execution-inference and execution-replay attacks by implementing a delegation model, achieving high throughput and low latency in WAN environments.