中文
相关论文

相关论文: Steering Away from Harm: An Adaptive Approach to D…

200 篇论文

Despite extensive efforts in safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks. Activation steering offers a training-free defense method but relies on fixed steering coefficients, resulting in suboptimal…

密码学与安全 · 计算机科学 2025-09-22 Weixiang Zhao , Jiahe Guo , Yulin Hu , Yang Deng , An Zhang , Xingyu Sui , Xinyang Han , Yanyan Zhao , Bing Qin , Tat-Seng Chua , Ting Liu

Vision Language Models (VLMs) have demonstrated impressive capabilities in integrating visual and textual information for understanding and reasoning, but remain highly vulnerable to adversarial attacks. While activation steering has…

计算机视觉与模式识别 · 计算机科学 2025-09-03 Sihao Wu , Gaojie Jin , Wei Huang , Jianhong Wang , Xiaowei Huang

As the capabilities of Vision Language Models (VLMs) continue to improve, they are increasingly targeted by jailbreak attacks. Existing defense methods face two major limitations: (1) they struggle to ensure safety without compromising the…

密码学与安全 · 计算机科学 2025-09-29 Xiyu Zeng , Siyuan Liang , Liming Lu , Haotian Zhu , Enguang Liu , Jisheng Dang , Yongbin Zhou , Shuchao Pang

As vision-language models (VLMs) are increasingly deployed in open-world scenarios, they can be easily induced by visual jailbreak attacks to generate harmful content, posing serious risks to model safety and trustworthy usage. Recent…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Xingyu Zhu , Beier Zhu , Shuo Wang , Junfeng Fang , Kesen Zhao , Hanwang Zhang , Xiangnan He

Despite extensive safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. However, existing methods generally lack the capability for continuous learning and self-evolution from interactions, limiting the…

密码学与安全 · 计算机科学 2026-04-21 Xu Liu , Yan Chen , Kan Ling , Yichi Zhu , Hengrun Zhang , Guisheng Fan , Huiqun Yu

Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks, where adversaries exploit textual or visual triggers to bypass safety guardrails. Recent…

密码学与安全 · 计算机科学 2026-05-15 Yi Wang , Hongye Qiu , Yue Xu , Sibei Yang , Zhan Qin , Minlie Huang , Wenjie Wang

The safety and reliability of vision-language models (VLMs) are a crucial part of deploying trustworthy agentic AI systems. However, VLMs remain vulnerable to jailbreaking attacks that undermine their safety alignment to yield harmful…

机器学习 · 计算机科学 2026-03-17 Ye Wang , Jing Liu , Toshiaki Koike-Akino

Large Vision-Language Models (VLMs) have achieved remarkable success in understanding complex real-world scenarios and supporting data-driven decision-making processes. However, VLMs exhibit significant vulnerability against adversarial…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Xiaosen Wang , Shaokang Wang , Zhijin Ge , Yuyang Luo , Shudong Zhang

Despite their superb capabilities, Vision-Language Models (VLMs) have been shown to be vulnerable to jailbreak attacks. While recent jailbreaks have achieved notable progress, their effectiveness and efficiency can still be improved. In…

计算机视觉与模式识别 · 计算机科学 2025-09-17 Yunhan Zhao , Xiang Zheng , Xingjun Ma

Vision-Language Models (VLMs) are now a core part of modern AI. Recent work proposed several visual jailbreak attacks using single/ holistic images. However, contemporary VLMs demonstrate strong robustness against such attacks due to…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Md Rafi Ur Rashid , MD Sadik Hossain Shanto , Vishnu Asutosh Dasu , Shagufta Mehnaz

Large Vision-Language Models (LVLMs) rely on attention-based retrieval of safety instructions to maintain alignment during generation. Existing attacks typically optimize image perturbations to maximize harmful output likelihood, but suffer…

计算机视觉与模式识别 · 计算机科学 2026-04-14 Jingru Li , Wei Ren , Tianqing Zhu

Activation steering has emerged as a powerful tool to shape LLM behavior without the need for weight updates. While its inherent brittleness and unreliability are well-documented, its safety implications remain underexplored. In this work,…

密码学与安全 · 计算机科学 2026-03-26 Yuxiao Li , Alina Fastowski , Efstratios Zaradoukas , Bardh Prenkaj , Gjergji Kasneci

Multimodal large language models (MLLMs) excel in vision-language tasks but also pose significant risks of generating harmful content, particularly through jailbreak attacks. Jailbreak attacks refer to intentional manipulations that bypass…

密码学与安全 · 计算机科学 2025-07-18 Yi Nian , Shenzhe Zhu , Yuehan Qin , Li Li , Ziyi Wang , Chaowei Xiao , Yue Zhao

Vision Language Models (VLMs) are increasingly being used in a broad range of applications, bringing their security and behavioral control to the forefront. While existing approaches for behavioral control or output redirection, like system…

计算机视觉与模式识别 · 计算机科学 2025-08-13 Mansi Phute , Ravikumar Balakrishnan

Vision-Language Models (VLMs) extend large language models with visual reasoning, but their multimodal design also introduces new, underexplored vulnerabilities. Existing multimodal red-teaming methods largely rely on brittle templates,…

密码学与安全 · 计算机科学 2026-05-27 Qilin Liao , Anamika Lochab , Ruqi Zhang

This work introduces SteerVLM, a lightweight steering module designed to guide Vision-Language Models (VLMs) towards outputs that better adhere to desired instructions. Our approach learns from the latent embeddings of paired prompts…

计算机视觉与模式识别 · 计算机科学 2025-10-31 Anushka Sivakumar , Andrew Zhang , Zaber Hakim , Chris Thomas

Large vision-language models (VLMs) often exhibit weakened safety alignment with the integration of the visual modality. Even when text prompts contain explicit harmful intent, adding an image can substantially increase jailbreak success…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Zhihua Wei , Qiang Li , Jian Ruan , Zhenxin Qin , Leilei Wen , Dongrui Liu , Wen Shen

Recent work has demonstrated the potential of contrastive steering for jailbreaking Large Language Models (LLMs). However, existing methods rely on limited and inherently biased contrastive prompts and require laborious manual tuning of…

密码学与安全 · 计算机科学 2026-05-21 Junxi Chen , Junhao Dong , Xiaohua Xie

Vision-language models (VLMs) have become central to tasks such as visual question answering, image captioning, and text-to-image generation. However, their outputs are highly sensitive to prompt variations, which can reveal vulnerabilities…

计算机视觉与模式识别 · 计算机科学 2026-02-02 Aarush Noheria , Yuguang Yao

Vision-language models (VLMs) have significantly advanced autonomous driving (AD) by enhancing reasoning capabilities. However, these models remain highly vulnerable to adversarial attacks. While existing research has primarily focused on…

计算机视觉与模式识别 · 计算机科学 2026-04-22 Tianyuan Zhang , Lu Wang , Xinwei Zhang , Yitong Zhang , Boyi Jia , Siyuan Liang , Shengshan Hu , Qiang Fu , Aishan Liu , Xianglong Liu
‹ 上一页 1 2 3 10 下一页 ›