Ruiyi Zhang

Opportunistic Backdoors (OPBackdoor), in which the backdoor objective is elicited only when the triggered prompt context presents an exploitable opportunity, enabling the model's think to disguise its pursuit through alibi-aligned reasoning that is logical with respect to the triggered prompt context but directly leads to the target response.

This work formulate state-conditioned minimal sufficient evidence recovery: given a captured agent state, recover a compact evidence combination that supplies the support its next decision still lacks.

Automating peer review to survive the flood of AI-generated papers creates an exploitable adversarial loop, incentivizing authors to game predictable evaluators and ultimately corrupting the downstream corpus used to train future frontier models.

Forgetting previous episodes in mixed-topic conversations can lead to significant accuracy drops, but TSIM shows how to maintain context integrity and improve performance in chat assistants.

A dynamic allocation strategy for prompt-injection detection can cut attack success rates by nearly half while improving response times.