99 citations · 149 across the 11 of their papers we have counts for
11 papers
TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors
Xia Du, Zhuosen Bao, Zheng Lin +4
Recent diffusion models have achieved remarkable realism in facial image synthesis, posing growing challenges to artificial intelligence-generated content (AIGC) forensic detectors…
LLM-Agnostic Semantic Representation Attack
Jiawei Lian, Jianhong Pan, Lefan Wang +4
Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting adversarial pr…
When Backdoors Meet Partial Observability: Attacking Real-World Reinforcement Learning
Tairan Huang, Qingqing Ye, Yulin Jin +4
Backdoor attacks can cause reinforcement learning (RL) policies to behave normally under clean inputs while executing malicious behaviors when triggers are present. Existing RL bac…
Semantic Representation Attack against Aligned Large Language Models
Jiawei Lian, Jianhong Pan, Lefan Wang +3
Large Language Models (LLMs) increasingly employ alignment techniques to prevent harmful outputs. Despite these safeguards, attackers can circumvent them by crafting prompts that i…
Revealing the Intrinsic Ethical Vulnerability of Aligned Large Language Models
Jiawei Lian, Jianhong Pan, Lefan Wang +3
Large language models (LLMs) are foundational explorations to artificial general intelligence, yet their alignment with human values via instruction tuning and preference learning…
Attack Anything: Blind DNNs via Universal Background Adversarial Attack
Jiawei Lian, Shaohui Mei, Xiaofei Wang +5
It has been widely substantiated that deep neural networks (DNNs) are susceptible and vulnerable to adversarial perturbations. Existing studies mainly focus on performing attacks b…
PADetBench: Towards Benchmarking Physical Attacks against Object Detection
Jiawei Lian, Jianhong Pan, Lefan Wang +3
Physical attacks against object detection have gained increasing attention due to their significant practical implications. However, conducting physical experiments is extremely ti…
A Comprehensive Study on the Robustness of Image Classification and Object Detection in Remote Sensing: Surveying and Benchmarking
Shaohui Mei, Jiawei Lian, Xiaofei Wang +3
Deep neural networks (DNNs) have found widespread applications in interpreting remote sensing (RS) imagery. However, it has been demonstrated in previous works that DNNs are vulner…
CBA: Contextual Background Attack against Optical Aerial Detection in the Physical World
Jiawei Lian, Xiaofei Wang, Yuru Su +2
Patch-based physical attacks have increasingly aroused concerns. However, most existing methods focus on obscuring targets captured on the ground, and some of these methods are sim…
Contextual adversarial attack against aerial detection in the physical world
Jiawei Lian, Xiaofei Wang, Yuru Su +2
Deep Neural Networks (DNNs) have been extensively utilized in aerial detection. However, DNNs' sensitivity and vulnerability to maliciously elaborated adversarial examples have pro…
Benchmarking Adversarial Patch Against Aerial Detection
Jiawei Lian, Shaohui Mei, Shun Zhang +1
DNNs are vulnerable to adversarial examples, which poses great security concerns for security-critical systems. In this paper, a novel adaptive-patch-based physical attack (AP-PA)…