AI Threat Alert
Benchmark LOW
AI Agent Systems: Architectures, Applications, and Evaluation
Bin Xu
AI agents -- systems that combine foundation models with reasoning, planning, memory, and tool use -- are rapidly becoming a practical interface...
AI Security Research
2,077+ academic papers on AI security, attacks, and defenses
Total
2,077
Attack
809
Benchmark
603
Defense
272
Tool
226
Survey
113
Showing 281–300 of 603 papers
Clear filters Benchmark MEDIUM
Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montage
Jinwei Hu, Xinmiao Huang, Youcheng Sun +2 more
As large language models (LLMs) transition to autonomous agents synthesizing real-time information, their reasoning capabilities introduce an...
Benchmark MEDIUM
JMedEthicBench: A Multi-Turn Conversational Benchmark for Evaluating Medical Safety in Japanese Large Language Models
Junyu Liu, Zirui Li, Qian Niu +7 more
As Large Language Models (LLMs) are increasingly deployed in healthcare field, it becomes essential to carefully evaluate their medical safety before...
Benchmark HIGH
How Real is Your Jailbreak? Fine-grained Jailbreak Evaluation with Anchored Reference
Songyang Liu, Chaozhuo Li, Rui Pu +5 more
Jailbreak attacks present a significant challenge to the safety of Large Language Models (LLMs), yet current automated evaluation methods largely...
Benchmark MEDIUM
Adaptive Hierarchical Evaluation of LLMs and SAST tools for CWE Prediction in Python
Muntasir Adnan, Carlos C. N. Kuhn
Large Language Models have become integral to software development, yet they frequently generate vulnerable code. Existing code vulnerability...
Benchmark MEDIUM
MCP-SandboxScan: WASM-based Secure Execution and Runtime Analysis for MCP Tools
Zhuoran Tan, Run Hao, Jeremy Singer +2 more
Tool-augmented LLM agents raise new security risks: tool executions can introduce runtime-only behaviors, including prompt injection and unintended...
Benchmark MEDIUM
Byzantine-Robust Federated Learning Framework with Post-Quantum Secure Aggregation for Real-Time Threat Intelligence Sharing in Critical IoT Infrastructure
Milad Rahmati, Nima Rahmati
The proliferation of Internet of Things devices in critical infrastructure has created unprecedented cybersecurity challenges, necessitating...
Benchmark MEDIUM
NOS-Gate: Queue-Aware Streaming IDS for Consumer Gateways under Timing-Controlled Evasion
Muhammad Bilal, Omer Tariq, Hasan Ahmed
Timing and burst patterns can leak through encryption, and an adaptive adversary can exploit them. This undermines metadata-only detection in a...
Benchmark LOW
ClinicalReTrial: A Self-Evolving AI Agent for Clinical Trial Protocol Optimization
Sixue Xing, Xuanye Xia, Kerui Wu +3 more
Clinical trial failure remains a central bottleneck in drug development, where minor protocol design flaws can irreversibly compromise outcomes...
Benchmark HIGH
An Empirical Evaluation of LLM-Based Approaches for Code Vulnerability Detection: RAG, SFT, and Dual-Agent Systems
Md Hasan Saju, Maher Muhtadi, Akramul Azim
The rapid advancement of Large Language Models (LLMs) presents new opportunities for automated software vulnerability detection, a crucial task in...
Benchmark MEDIUM
Encyclo-K: Evaluating LLMs with Dynamically Composed Knowledge Statements
Yiming Liang, Yizhi Li, Yantao Du +14 more
Benchmarks play a crucial role in tracking the rapid advancement of large language models (LLMs) and identifying their capability boundaries....
Benchmark MEDIUM
PriceSeer: Evaluating Large Language Models in Real-Time Stock Prediction
Bohan Liang, Zijian Chen, Qi Jia +3 more
Stock prediction, a subject closely related to people's investment activities in fully dynamic and live environments, has been widely studied....
Benchmark MEDIUM
Safe in the Future, Dangerous in the Past: Dissecting Temporal and Linguistic Vulnerabilities in LLMs
Muhammad Abdullahi Said, Muhammad Sammani Sani
As Large Language Models (LLMs) integrate into critical global infrastructure, the assumption that safety alignment transfers zero-shot from English...
Benchmark HIGH
Language Model Agents Under Attack: A Cross Model-Benchmark of Profit-Seeking Behaviors in Customer Service
Jingyu Zhang
Customer-service LLM agents increasingly make policy-bound decisions (refunds, rebooking, billing disputes), but the same ``helpful'' interaction...
Benchmark MEDIUM
Taming Hallucinations: Boosting MLLMs' Video Understanding via Counterfactual Video Generation
Zhe Huang, Hao Wen, Aiming Hao +6 more
Multimodal Large Language Models (MLLMs) have made remarkable progress in video understanding. However, they suffer from a critical vulnerability: an...
Benchmark MEDIUM
Enhanced Web Payload Classification Using WAMM: An AI-Based Framework for Dataset Refinement and Model Evaluation
Heba Osama, Omar Elebiary, Youssef Qassim +4 more
Web applications increasingly face evasive and polymorphic attack payloads, yet traditional web application firewalls (WAFs) based on static rule...
Benchmark HIGH
Prompt-Induced Over-Generation as Denial-of-Service: A Black-Box Attack-Side Benchmark
Manu, Yi Guo, Kanchana Thilakarathna +5 more
Large Language Models (LLMs) can be driven into over-generation, emitting thousands of tokens before producing an end-of-sequence (EOS) token. This...
Benchmark MEDIUM
It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents
Karolina Korgul, Yushi Yang, Arkadiusz Drohomirecki +7 more
Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their reliance...
Benchmark LOW
Is Chain-of-Thought Really Not Explainability? Chain-of-Thought Can Be Faithful without Hint Verbalization
Kerem Zaman, Shashank Srivastava
Recent work, using the Biasing Features metric, labels a CoT as unfaithful if it omits a prompt-injected hint that affected the prediction. We argue...
Benchmark HIGH
Rethinking the Capability of Fine-Tuned Language Models for Automated Vulnerability Repair
Woorim Han, Yeongjun Kwak, Miseon Yu +4 more
Learning-based automated vulnerability repair (AVR) techniques that utilize fine-tuned language models have shown promise in generating vulnerability...
Track AI security vulnerabilities in real time
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