2,560+ academic papers on AI security, attacks, and defenses
Showing 421–440 of 635 papers
Clear filtersHao Wu, Prateek Saxena
This paper explores attacks and defenses on vector databases in retrieval-augmented generation (RAG) systems. Prior work on knowledge poisoning...
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...
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...
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...
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...
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, Ananya Mujoo
Multi-turn conversational attacks, which leverage psychological principles like Foot-in-the-Door (FITD), where a small initial request paves the way...
Yanxi Li, Ruocheng Shan
Large language models are increasingly used for text classification tasks such as sentiment analysis, yet their reliance on natural language prompts...
Yanting Wang, Runpeng Geng, Jinghui Chen +2 more
Many recent studies showed that LLMs are vulnerable to jailbreak attacks, where an attacker can perturb the input of an LLM to induce it to generate...
Pinaki Prasad Guha Neogi, Ahmad Mohammadshirazi, Dheeraj Kulshrestha +1 more
Mixture-of-Experts (MoE) architectures are increasingly adopted in large language models (LLMs) for their scalability and efficiency. However, their...
Junrui Zhang, Xinyu Zhao, Jie Peng +3 more
Multimodal learning has shown significant superiority on various tasks by integrating multiple modalities. However, the interdependencies among...
Oluleke Babayomi, Dong-Seong Kim
Electric Vehicle (EV) charging infrastructure faces escalating cybersecurity threats that can severely compromise operational efficiency and grid...
Yunyi Zhang, Shibo Cui, Baojun Liu +4 more
LLM applications (i.e., LLM apps) leverage the powerful capabilities of LLMs to provide users with customized services, revolutionizing traditional...
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