2,560+ academic papers on AI security, attacks, and defenses
Showing 661–680 of 982 papers
Clear filtersK. J. Kevin Feng, Tae Soo Kim, Rock Yuren Pang +3 more
AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their...
Haoyu Shen, Weimin Lyu, Haotian Xu +1 more
Vision-Language Models (VLMs) have achieved impressive progress in multimodal text generation, yet their rapid adoption raises increasing concerns...
Mohammad M Maheri, Xavier Cadet, Peter Chin +1 more
Approximate machine unlearning aims to efficiently remove the influence of specific data points from a trained model, offering a practical...
Tong Wu, Weibin Wu, Zibin Zheng
Equipped with various tools and knowledge, GPTs, one kind of customized AI agents based on OpenAI's large language models, have illustrated great...
Zeng Wang, Minghao Shao, Akashdeep Saha +4 more
Graph neural networks (GNNs) have shown promise in hardware security by learning structural motifs from netlist graphs. However, this reliance on...
Richard J. Young
Large Language Model (LLM) safety guardrail models have emerged as a primary defense mechanism against harmful content generation, yet their...
Tianyu Zhang, Zihang Xi, Jingyu Hua +1 more
In the realm of black-box jailbreak attacks on large language models (LLMs), the feasibility of constructing a narrow safety proxy, a lightweight...
Herman Errico, Jiquan Ngiam, Shanita Sojan
The Model Context Protocol (MCP) replaces static, developer-controlled API integrations with more dynamic, user-driven agent systems, which also...
Kaiyuan Zhang, Mark Tenenholtz, Kyle Polley +3 more
The integration of artificial intelligence (AI) agents into web browsers introduces security challenges that go beyond traditional web application...
Jakub Hoscilowicz, Artur Janicki
We introduce the Adversarial Confusion Attack, a new class of threats against multimodal large language models (MLLMs). Unlike jailbreaks or targeted...
Sidahmed Benabderrahmane, James Cheney, Talal Rahwan
Advanced Persistent Threats (APTs) pose a significant challenge in cybersecurity due to their stealthy and long-term nature. Modern supervised...
Sen Nie, Jie Zhang, Jianxin Yan +2 more
Adversarial attacks have evolved from simply disrupting predictions on conventional task-specific models to the more complex goal of manipulating...
Steven Peh
Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production...
Yingjia Shang, Yi Liu, Huimin Wang +4 more
With the rapid advancement of retrieval-augmented vision-language models, multimodal medical retrieval-augmented generation (MMed-RAG) systems are...
Md Akil Raihan Iftee, Syed Md. Ahnaf Hasan, Amin Ahsan Ali +3 more
Test-time personalization in federated learning enables models at clients to adjust online to local domain shifts, enhancing robustness and...
Xurui Li, Kaisong Song, Rui Zhu +2 more
Large Language Models (LLMs) have developed rapidly in web services, delivering unprecedented capabilities while amplifying societal risks. Existing...
Yixin Wu, Rui Wen, Chi Cui +2 more
Inference attacks have been widely studied and offer a systematic risk assessment of ML services; however, their implementation and the attack...
Ryan Wong, Hosea David Yu Fei Ng, Dhananjai Sharma +2 more
Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work...
Adarsh Kumarappan, Ayushi Mehrotra
The SmoothLLM defense provides a certification guarantee against jailbreaking attacks, but it relies on a strict "k-unstable" assumption that rarely...
Adarsh Kumarappan, Ananya Mujoo
Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way...
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