3 citations · 4 across the 16 of their papers we have counts for
16 papers
CertVLA: Certified Defense against Physical Visual Attacks for Vision-Language-Action Models
Hui Lu, Zhijie Peng, Yuqi Lin +8
Vision-Language-Action (VLA) policies are vulnerable to localized physical perturbations, yet existing certified patch defenses target discrete labels and cannot directly certify c…
ARENA: Automated Red-Teaming for Large Audio Language Models
Jiaming He, Zhicong Huang, Tian Jin +5
Large audio-language models (LALMs) make it possible to interact with language models through speech, music, and environmental sound, but they also introduce a safety surface that…
TRACE: Trajectory-Based Safety Patch Learning for LLM Post-Training Realignment
Changyue Li, Jiaming He, Youliang Yuan +4
Fine-Tuning-as-a-Service (FTaaS) platforms let users perform supervised fine-tuning (SFT) on customized data, but this pipeline can erode model safety alignment. To recover safety…
ChronoLock: Protecting Videos from Unauthorized Text-to-Video Personalization
Jiaming He, Jiashu Zhang, Guanyu Hou +4
Text-to-video (T2V) diffusion models have made it increasingly easy to synthesize realistic and temporally coherent videos, while recent personalization techniques allow such model…
STARS: Spike Tail-Aware Relational Synthesis for ANN-to-SNN Data-Free Knowledge Distillation
Shuhan Ye, Yi Yu, Qixin Zhang +5
SNNs promise energy-efficient and low-latency inference, but their performance still trails that of ANNs. ANN-to-SNN knowledge distillation helps narrow this gap, yet the original…
Spectral Defense Against Resource-Targeting Attack in 3D Gaussian Splatting
Yang Chen, Yi Yu, Jiaming He +3
Recent advances in 3D Gaussian Splatting (3DGS) deliver high-quality rendering, yet the Gaussian representation exposes a new attack surface, the resource-targeting attack. This at…
UTOPIA: Unlearnable Tabular Data via Decoupled Shortcut Embedding
Jiaming He, Fuming Luo, Hongwei Li +5
Unlearnable examples (UE) have emerged as a practical mechanism to prevent unauthorized model training on private vision data, while extending this protection to tabular data is no…
TEAR: Temporal-aware Automated Red-teaming for Text-to-Video Models
Jiaming He, Guanyu Hou, Hongwei Li +6
Text-to-Video (T2V) models are capable of synthesizing high-quality, temporally coherent dynamic video content, but the diverse generation also inherently introduces critical safet…
Semantic Router: On the Feasibility of Hijacking MLLMs via a Single Adversarial Perturbation
Changyue Li, Jiaying Li, Youliang Yuan +3
Multimodal Large Language Models (MLLMs) are increasingly deployed in stateless systems, such as autonomous driving and robotics. This paper investigates a novel threat: Semantic-A…
BadDepth: Backdoor Attacks Against Monocular Depth Estimation in the Physical World
Ji Guo, Long Zhou, Zhijin Wang +4
In recent years, deep learning-based Monocular Depth Estimation (MDE) models have been widely applied in fields such as autonomous driving and robotics. However, their vulnerabilit…
Evaluating Robustness of Large Audio Language Models to Audio Injection: An Empirical Study
Guanyu Hou, Jiaming He, Yinhang Zhou +4
Large Audio-Language Models (LALMs) are increasingly deployed in real-world applications, yet their robustness against malicious audio injection attacks remains underexplored. This…
BadRefSR: Backdoor Attacks Against Reference-based Image Super Resolution
Xue Yang, Tao Chen, Lei Guo +4
Reference-based image super-resolution (RefSR) represents a promising advancement in super-resolution (SR). In contrast to single-image super-resolution (SISR), RefSR leverages an…
TrojanEdit: Multimodal Backdoor Attack Against Image Editing Model
Ji Guo, Peihong Chen, Wenbo Jiang +6
Multimodal diffusion models for image editing generate outputs conditioned on both textual instructions and visual inputs, aiming to modify target regions while preserving the rest…
Combinational Backdoor Attack against Customized Text-to-Image Models
Wenbo Jiang, Jiaming He, Hongwei Li +6
Recently, Text-to-Image (T2I) synthesis technology has made tremendous strides. Numerous representative T2I models have emerged and achieved promising application outcomes, such as…
Backdoor Attacks against Image-to-Image Networks
Wenbo Jiang, Hongwei Li, Jiaming He +4
Recently, deep learning-based Image-to-Image (I2I) networks have become the predominant choice for I2I tasks such as image super-resolution and denoising. Despite their remarkable…
Watch Out for Your Guidance on Generation! Exploring Conditional Backdoor Attacks against Large Language Models
Jiaming He, Wenbo Jiang, Guanyu Hou +3
Mainstream backdoor attacks on large language models (LLMs) typically set a fixed trigger in the input instance and specific responses for triggered queries. However, the fixed tri…