Jiaheng Zhang

STEP introduces a novel, black-box, retraining-free detector that profiles audio samples using dual perturbation branches to detect backdoor attacks by exploiting the characteristic instability of hidden triggers.

ARuleCon is an agentic framework that autonomously and accurately converts security rules across heterogeneous SIEM platforms, significantly outperforming baseline LLMs in fidelity.

The paper introduces AudioHijack, a framework that successfully demonstrates context-agnostic and imperceptible auditory prompt injection attacks, showing that commercial Large Audio-Language Models can be hijacked with high success rates.

The paper introduces BadDLM, a unified framework that demonstrates a new class of backdoor vulnerabilities in Diffusion Language Models (DLMs) by exploiting their forward masking process across diverse targets.

The paper proposes defining 'intent-to-execution integrity' as the necessary end-to-end correctness property for securing LLM agents, arguing that current defenses are insufficient due to untrusted components.

SAMark introduces a self-anchored text watermarking framework that achieves high robustness (up to 90.2% TP@FP1%) against challenging paragraph-level paraphrasing attacks by establishing a step-independent green region in semantic space.

The paper proposes BiCoT, a novel watermarking framework that embeds ownership signals into the internal structure of Chain-of-Thought reasoning traces, achieving robust detection without compromising the model's reasoning fidelity.

AliMark proposes a novel watermarking framework that treats sentence-level watermarking as a bit sequence alignment problem, significantly enhancing robustness against structural text perturbations like sentence splitting and merging.

AliMark proposes a novel framework that enhances the robustness of sentence-level watermarking by reformulating the problem as a bit sequence encoding and alignment task, significantly improving resilience against structural text perturbations like sentence splitting and merging.