2,589+ academic papers on AI security, attacks, and defenses
Showing 1361–1380 of 2,589 papers
Yuansen Liu, Yixuan Tang, Anthony Kum Hoe Tun
Current LLM safety research predominantly focuses on mitigating Goal Hijacking, preventing attackers from redirecting a model's high-level objective...
Murat Bilgehan Ertan, Marten van Dijk
Differentially Private Stochastic Gradient Descent (DP-SGD) is the dominant paradigm for private training, but its fundamental limitations under...
Hao Li, Yankai Yang, G. Edward Suh +2 more
Large Language Models (LLMs) have enabled the development of powerful agentic systems capable of automating complex workflows across various fields....
Yutao Mou, Zhangchi Xue, Lijun Li +4 more
While LLM-based agents can interact with environments via invoking external tools, their expanded capabilities also amplify security risks....
Jiawen Zhang, Yangfan Hu, Kejia Chen +7 more
Fine-tuning is an essential and pervasive functionality for applying large language models (LLMs) to downstream tasks. However, it has the potential...
Mohoshin Ara Tahera, Karamveer Singh Sidhu, Shuvalaxmi Dass +1 more
Large Language Models (LLMs) are increasingly adopted in healthcare to support clinical decision-making, summarize electronic health records (EHRs),...
Hanna Foerster, Tom Blanchard, Kristina Nikolić +6 more
AI agents are vulnerable to prompt injection attacks, where malicious content hijacks agent behavior to steal credentials or cause financial loss....
Sara AlMahri, Liming Xu, Alexandra Brintrup
Modern supply chains are increasingly exposed to disruptions from geopolitical events, demand shocks, trade restrictions, to natural disasters. While...
Oleg Brodt, Elad Feldman, Bruce Schneier +1 more
Prompt injection was initially framed as the large language model (LLM) analogue of SQL injection. However, over the past three years, attacks...
Zhiyi Mou, Jingyuan Yang, Zeheng Qian +6 more
While Large Language Models (LLMs) have powerful capabilities, they remain vulnerable to jailbreak attacks, which is a critical barrier to their safe...
Greta Dolcetti, Giulio Zizzo, Sergio Maffeis
We present an experimental evaluation that assesses the robustness of four open source LLMs claiming function-calling capabilities against three...
Feng Zhang, Shijia Li, Chunmao Zhang +7 more
User simulators serve as the critical interactive environment for agent post-training, and an ideal user simulator generalizes across domains and...
Caitlin A. Stamatis, Jonah Meyerhoff, Richard Zhang +3 more
Large language models (LLMs) are increasingly used for mental health support, yet existing safety evaluations rely primarily on small,...
Xiaonan Liu, Zhihao Li, Xiao Lan +3 more
Capture-the-Flag (CTF) competitions play a central role in modern cybersecurity as a platform for training practitioners and evaluating offensive and...
Fengchao Chen, Tingmin Wu, Van Nguyen +1 more
Large Language Models (LLMs) have enabled agents to move beyond conversation toward end-to-end task execution and become more helpful. However, this...
Shaznin Sultana, Sadia Afreen, Nasir U. Eisty
Context: Traditional software security analysis methods struggle to keep pace with the scale and complexity of modern codebases, requiring...
Renyang Liu, Kangjie Chen, Han Qiu +4 more
Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from...
Ziqi Ding, Yunfeng Wan, Wei Song +7 more
CAPTCHAs are widely used by websites to block bots and spam by presenting challenges that are easy for humans but difficult for automated programs to...
Seong-Gyu Park, Sohee Park, Jisu Lee +2 more
Recent LLMs increasingly integrate reasoning mechanisms like Chain-of-Thought (CoT). However, this explicit reasoning exposes a new attack surface...
Erin Feiglin, Nir Hutnik, Raz Lapid
We investigate a failure mode of large language models (LLMs) in which plain-text prompts elicit excessive outputs, a phenomenon we term Overflow....
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