2,529+ academic papers on AI security, attacks, and defenses
Showing 101–120 of 867 papers
Clear filtersWenkui Yang, Chao Jin, Haisu Zhu +7 more
Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is...
Cheng Liu, Xiaolei Liu, Xingyu Li +2 more
Existing jailbreak defense paradigms primarily rely on static detection of prompts, outputs, or internal states, often neglecting the dynamic...
Luat Do, Jiao Yin, Jinli Cao +1 more
Software vulnerabilities continue to pose significant threats to modern information systems, requiring a timely and accurate risk assessment. Public...
Zhiheng Li, Zongyang Ma, Yuntong Pan +8 more
Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a...
Zhiheng Li, Zongyang Ma, Yuntong Pan +8 more
Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a...
Ziye Wang, Guanyu Wang, Kailong Wang
Retrieval-Augmented Generation (RAG) significantly enhances Large Language Models (LLMs), but simultaneously exposes a critical vulnerability to...
Yizhe Zeng, Wei Zhang, Yunpeng Li +3 more
While Chain-of-Thought (CoT) prompting has become a standard paradigm for eliciting complex reasoning capabilities in Large Language Models, it...
Zi Liang, Qipeng Xie, Jun He +7 more
Recent advancements in Large Language Models (LLMs) have sparked interest in their application to Static Application Security Testing (SAST),...
Phan The Duy, Nguyen Viet Duy, Khoa Ngo-Khanh +2 more
While recent approaches leverage large language models (LLMs) and multi-agent pipelines to automatically generate proof-of-concept (PoC) exploits...
Adrian Shuai Li, Md Ajwad Akil, Elisa Bertino
Concept drift and adversarial evasion are two major challenges for deploying machine learning-based malware detectors. While both have been studied...
Manish Bhatt, Sarthak Munshi, Vineeth Sai Narajala +4 more
We prove that no continuous, utility-preserving wrapper defense-a function $D: X\to X$ that preprocesses inputs before the model sees them-can make...
Zonghao Ying, Haowen Dai, Lianyu Hu +5 more
Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and...
Zonghao Ying, Haowen Dai, Lianyu Hu +5 more
Modern text-to-image (T2I) models can now render legible, paragraph-length text, enabling a fundamentally new class of misuse. We identify and...
Yiyang Zhang, Chaojian Yu, Ziming Hong +4 more
Multimodal pretrained models are vulnerable to backdoor attacks, yet most existing methods rely on visual or multimodal triggers, which are...
Baoshun Tong, Haoran He, Ling Pan +2 more
Vision-Language-Action (VLA) models have achieved remarkable success in robotic manipulation. However, their robustness to linguistic nuances remains...
Yanxu Mao, Peipei Liu, Tiehan Cui +3 more
With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team...
Qingyang Xu, Yaling Shen, Stephanie Fong +7 more
The increasing use of large language models (LLMs) in mental healthcare raises safety concerns in high-stakes therapeutic interactions. A key...
Charafeddine Mouzouni
LLM agents with tool access can discover and exploit security vulnerabilities. This is known. What is not known is which features of a system prompt...
Zhuowen Yuan, Zhaorun Chen, Zhen Xiang +5 more
Existing research on LLM agent security mainly focuses on prompt injection and unsafe input/output behaviors. However, as agents increasingly rely on...
Siyuan Li, Zehao Liu, Xi Lin +6 more
As Large Language Models (LLMs) are increasingly deployed in complex applications, their vulnerability to adversarial attacks raises urgent safety...
Get breaking CVE alerts, compliance reports (ISO 42001, EU AI Act), and CISO risk assessments for your AI/ML stack.
Start 14-Day Free Trial
AI Threat Alert