Lan Zhang

The paper introduces IOCRegex-gen, an automated LLM-based system that converts Indicators of Compromise (IOCs) into syntactically and semantically correct regular expressions, achieving high accuracy in large-scale CTI processing.

The paper proposes a novel method to generate adversarial malware samples that evade deep learning detectors while simultaneously minimizing the detectable 'drift' signals, showing that similarity constraints are key to this balance.

The paper demonstrates that static malware classifiers often rely on superficial artifacts like packing and metadata rather than true malicious semantics, using the TRUSTEE interpretability tool to diagnose this bias.

Permit is a novel framework that enforces fine-grained, permission-aware control over the hidden states of LLMs, preventing information leakage even when sensitive data is present in the context.

This paper identifies and explores a new type of physical adversarial attack on vision systems called Scratch-induced Lens Adversarial Streak Hijacking (SLASH), which causes persistent and selective optical artifacts through small scratches on camera lenses or protective covers.