2,077+ academic papers on AI security, attacks, and defenses
Showing 301–320 of 522 papers
Clear filtersAfshin Khadangi, Hanna Marxen, Amir Sartipi +2 more
Frontier large language models (LLMs) such as ChatGPT, Grok and Gemini are increasingly used for mental-health support with anxiety, trauma and...
Ziyi Tong, Feifei Sun, Le Minh Nguyen
Large Multimodal Language Models (MLLMs) are emerging as one of the foundational tools in an expanding range of applications. Consequently,...
Yuanhe Zhang, Weiliu Wang, Zhenhong Zhou +5 more
Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in reasoning, planning, and tool usage. The recently proposed Model...
Haowei Fu, Bo Ni, Han Xu +3 more
Retrieval-Augmented Generation (RAG) and Supervised Finetuning (SFT) have become the predominant paradigms for equipping Large Language Models (LLMs)...
Omar Farooq Khan Suri, John McCrae
Large Language Models (LLMs) are increasingly being deployed in real-world applications, but their flexibility exposes them to prompt injection...
Zihao Wang, Kar Wai Fok, Vrizlynn L. L. Thing
Multi-modal large language models (MLLMs), capable of processing text, images, and audio, have been widely adopted in various AI applications....
Mintong Kang, Chong Xiang, Sanjay Kariyappa +3 more
Indirect prompt injection attacks (IPIAs), where large language models (LLMs) follow malicious instructions hidden in input data, pose a critical...
Hao 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...
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