2,077+ academic papers on AI security, attacks, and defenses
Showing 1–20 of 347 papers
Clear filtersXingyu Zhu, Beier Zhu, Shuo Wang +4 more
As vision-language models (VLMs) are increasingly deployed in open-world scenarios, they can be easily induced by visual jailbreak attacks to...
Zhanguang Zhang, Zhiyuan Li, Behnam Rahmati +10 more
Robot action planning in the real world is challenging as it requires not only understanding the current state of the environment but also predicting...
Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera
Large language models are becoming pervasive core components in many real-world applications. As a consequence, security alignment represents a...
Rui Yang Tan, Yujia Hu, Roy Ka-Wei Lee
Multimodal Large Language Models (MLLMs) extend text-only LLMs with visual reasoning, but also introduce new safety failure modes under visually...
Mohammad Asadi, Jack W. O'Sullivan, Fang Cao +5 more
Multimodal AI systems have achieved remarkable performance across a broad range of real-world tasks, yet the mechanisms underlying visual-language...
Yanming Mu, Hao Hu, Feiyang Li +7 more
Retrieval-Augmented Generation (RAG) significantly mitigates the hallucinations and domain knowledge deficiency in large language models by...
Charoes Huang, Xin Huang, Amin Milani Fard
Prompt injection is listed as the number-one vulnerability class in the OWASP Top 10 for LLM Applications that can subvert LLM guardrails, disclose...
Zhongyi Li, Wan Tian, Jingyu Chen +8 more
Multi-agent collaboration has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models, yet it suffers from...
Huamin Chen, Xunzhuo Liu, Bowei He +5 more
Over the past year, the vLLM Semantic Router project has released a series of work spanning: (1) core routing mechanisms -- signal-driven routing,...
Zongjie Li, Chaozheng Wang, Yuchong Xie +2 more
Large Language Models are increasingly being considered for deployment in safety-critical military applications. However, current benchmarks suffer...
Kwanyoung Kim, Byeongsu Sim
Reinforcement learning from human feedback (RLHF) has proven effective in aligning large language models with human preferences, inspiring the...
Zihui Chen, Yuling Wang, Pengfei Jiao +4 more
Text-attributed graphs (TAGs) enhance graph learning by integrating rich textual semantics and topological context for each node. While boosting...
Octavian Untila
An autonomous AI ecosystem (SUBSTRATE S3), generating product specifications without explicit instructions about formal methods, independently...
Yasamin Medghalchi, Milad Yazdani, Amirhossein Dabiriaghdam +7 more
Ultrasound is widely used in clinical practice due to its portability, cost-effectiveness, safety, and real-time imaging capabilities. However, image...
Zihan Guo, Zhiyu Chen, Xiaohang Nie +3 more
With the rapid evolution of Large Language Model (LLM) agent ecosystems, centralized skill marketplaces have emerged as pivotal infrastructure for...
Abed K. Musaffar, Ambuj Singh, Francesco Bullo
Large language models (LLMs) are increasingly deployed in human-AI teams as support agents for complex tasks such as information retrieval,...
Xinyue Liu, Niloofar Mireshghallah, Jane C. Ginsburg +1 more
Frontier LLM companies have repeatedly assured courts and regulators that their models do not store copies of training data. They further rely on...
Uchi Uchibeke
AI agents today have passwords but no permission slips. They execute tool calls (fund transfers, database queries, shell commands, sub-agent...
Shouqiao Wang, Marcello Politi, Samuele Marro +1 more
As agentic systems move into real-world deployments, their decisions increasingly depend on external inputs such as retrieved content, tool outputs,...
Yandan Zheng, Haoran Luo, Zhenghong Lin +2 more
Benchmarks are the de facto standard for tracking progress in large language models (LLMs), yet static test sets can rapidly saturate, become...
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