Li Lu

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Red-Teaming & Adversarial Robustness (2)Speech & Audio (2)Multimodal Models (1)

Frequent co-authors

Kun Wang (2)Jiaheng Zhang (2)Meng Chen (1)Jiaheng Zhang (1)

Papers (2)

Apr 16, 2026

Meng Chen +5Apr 16, 2026

Hijacking Large Audio-Language Models via Context-Agnostic and Imperceptible Auditory Prompt Injection

LALMs are shockingly vulnerable to inaudible audio prompts that can make them execute unauthorized actions, even on commercial systems like Mistral AI and Microsoft Azure.

Meng Chen, Kun Wang, Li Lu +3

Multimodal Models Red-Teaming & Adversarial Robustness Speech & Audio

Mar 18, 2026

Mar 18, 2026·also XJTU

STEP: Detecting Audio Backdoor Attacks via Stability-based Trigger Exposure Profiling

Audio backdoor attacks leave a tell: triggers are surprisingly stable to destructive noise but fragile to meaning-preserving changes.

Kun Wang, Meng Chen, Junhao Wang +5

Red-Teaming & Adversarial Robustness Speech & Audio

Search

Li Lu

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)