2,077+ academic papers on AI security, attacks, and defenses
Showing 1–16 of 16 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...
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...
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...
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...
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,...
Matta Varun, Ajay Kumar Dhakar, Yuan Hong +1 more
Graph neural network (GNN) is a powerful tool for analyzing graph-structured data. However, their vulnerability to adversarial attacks raises serious...
Sen Fang, Weiyuan Ding, Zhezhen Cao +2 more
Large Language Models (LLMs) are increasingly adopted for vulnerability detection, yet their reasoning remains fundamentally unsound. We identify a...
Yusheng Zheng, Yiwei Yang, Wei Zhang +1 more
LLM agent frameworks increasingly offer checkpoint-restore for error recovery and exploration, advising developers to make external tool calls safe...
Wenjing Hong, Zhonghua Rong, Li Wang +5 more
Large Language Models (LLMs) have been widely deployed, especially through free Web-based applications that expose them to diverse user-generated...
Toan Tran, Olivera Kotevska, Li Xiong
Membership inference attacks (MIAs), which enable adversaries to determine whether specific data points were part of a model's training dataset, have...
Aravind Krishnan, Karolina Stańczak, Dietrich Klakow
As Spoken Language Models (SLMs) integrate speech and text modalities, they inherit the safety vulnerabilities of their LLM backbone and an expanded...
Sheng Liu, Panos Papadimitratos
FL has emerged as a transformative paradigm for ITS, notably camera-based Road Condition Classification (RCC). However, by enabling collaboration,...
Dimitris Mitropoulos, Nikolaos Alexopoulos, Georgios Alexopoulos +1 more
Security code reviews increasingly rely on systems integrating Large Language Models (LLMs), ranging from interactive assistants to autonomous agents...
Mohammadhossein Homaei, Iman Khazrak, Rubén Molano +2 more
Industrial Cyber-Physical Systems (ICPS) face growing threats from cyber-attacks that exploit sensor and control vulnerabilities. Digital Twin (DT)...
Jiahao Zhang, Yilong Wang, Suhang Wang
Graph neural networks (GNNs) are widely used for learning from graph-structured data in domains such as social networks, recommender systems, and...
Md Takrim Ul Alam, Akif Islam, Mohd Ruhul Ameen +2 more
Large language models (LLMs) deployed behind APIs and retrieval-augmented generation (RAG) stacks are vulnerable to prompt injection attacks that may...
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