30 citations · 43 across the 7 of their papers we have counts for
7 papers
Sparse Tokens Suffice: Jailbreaking Audio Language Models via Token-Aware Gradient Optimization
Zheng Fang, Xiaosen Wang, Shenyi Zhang +2
Jailbreak attacks on audio language models (ALMs) optimize audio perturbations to elicit unsafe generations, and they typically update the entire waveform densely throughout optimi…
Devling into Adversarial Transferability on Image Classification: Review, Benchmark, and Evaluation
Xiaosen Wang, Zhijin Ge, Bohan Liu +5
Adversarial transferability refers to the capacity of adversarial examples generated on the surrogate model to deceive alternate, unexposed victim models. This property eliminates…
Security Risk of Misalignment between Text and Image in Multi-modal Model
Xiaosen Wang, Zhijin Ge, Shaokang Wang
Despite the notable advancements and versatility of multi-modal diffusion models, such as text-to-image models, their susceptibility to adversarial inputs remains underexplored. Co…
Disrupting Semantic and Abstract Features for Better Adversarial Transferability
Yuyang Luo, Xiaosen Wang, Zhijin Ge +1
Adversarial examples pose significant threats to deep neural networks (DNNs), and their property of transferability in the black-box setting has led to the emergence of transfer-ba…
Attention! Your Vision Language Model Could Be Maliciously Manipulated
Xiaosen Wang, Shaokang Wang, Zhijin Ge +2
Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VL…
Improving the Transferability of Adversarial Examples with Arbitrary Style Transfer
Zhijin Ge, Fanhua Shang, Hongying Liu +4
Deep neural networks are vulnerable to adversarial examples crafted by applying human-imperceptible perturbations on clean inputs. Although many attack methods can achieve high suc…
Boosting Adversarial Transferability by Achieving Flat Local Maxima
Zhijin Ge, Hongying Liu, Xiaosen Wang +2
Transfer-based attack adopts the adversarial examples generated on the surrogate model to attack various models, making it applicable in the physical world and attracting increasin…