AI Threat Alert
Benchmark LOW
Box Maze: A Process-Control Architecture for Reliable LLM Reasoning
Zou Qiang
Large language models (LLMs) demonstrate strong generative capabilities but remain vulnerable to hallucination and unreliable reasoning under...
AI Security Research
2,542+ academic papers on AI security, attacks, and defenses
Total
2,542
Attack
976
Benchmark
730
Defense
347
Tool
274
Survey
143
Showing 141–160 of 552 papers
Clear filters Benchmark MEDIUM
Functional Subspace Watermarking for Large Language Models
Zikang Ding, Junhao Li, Suling Wu +3 more
Model watermarking utilizes internal representations to protect the ownership of large language models (LLMs). However, these features inevitably...
Benchmark LOW
The Validity Gap in Health AI Evaluation: A Cross-Sectional Analysis of Benchmark Composition
Alvin Rajkomar, Pavan Sudarshan, Angela Lai +1 more
Background: Clinical trials rely on transparent inclusion criteria to ensure generalizability. In contrast, benchmarks validating health-related...
Benchmark HIGH
Machine Learning for Network Attacks Classification and Statistical Evaluation of Machine Learning for Network Attacks Classification and Adversarial Learning Methodologies for Synthetic Data Generation
Iakovos-Christos Zarkadis, Christos Douligeris
Supervised detection of network attacks has always been a critical part of network intrusion detection systems (NIDS). Nowadays, in a pivotal time...
Benchmark MEDIUM
Parameter-Efficient Modality-Balanced Symmetric Fusion for Multimodal Remote Sensing Semantic Segmentation
Haocheng Li, Juepeng Zheng, Shuangxi Miao +4 more
Multimodal remote sensing semantic segmentation enhances scene interpretation by exploiting complementary physical cues from heterogeneous data....
Benchmark MEDIUM
WeatherReasonSeg: A Benchmark for Weather-Aware Reasoning Segmentation in Visual Language Models
Wanjun Du, Zifeng Yuan, Tingting Chen +3 more
Existing vision-language models (VLMs) have demonstrated impressive performance in reasoning-based segmentation. However, current benchmarks are...
Benchmark MEDIUM
VeriGrey: Greybox Agent Validation
Yuntong Zhang, Sungmin Kang, Ruijie Meng +2 more
Agentic AI has been a topic of great interest recently. A Large Language Model (LLM) agent involves one or more LLMs in the back-end. In the front...
Benchmark LOW
InfoDensity: Rewarding Information-Dense Traces for Efficient Reasoning
Chengwei Wei, Jung-jae Kim, Longyin Zhang +2 more
Large Language Models (LLMs) with extended reasoning capabilities often generate verbose and redundant reasoning traces, incurring unnecessary...
Benchmark LOW
MedCL-Bench: Benchmarking stability-efficiency trade-offs and scaling in biomedical continual learning
Min Zeng, Shuang Zhou, Zaifu Zhan +1 more
Medical language models must be updated as evidence and terminology evolve, yet sequential updating can trigger catastrophic forgetting. Although...
Benchmark MEDIUM
Differential Harm Propensity in Personalized LLM Agents: The Curious Case of Mental Health Disclosure
Caglar Yildirim
Large language models (LLMs) are increasingly deployed as tool-using agents, shifting safety concerns from harmful text generation to harmful task...
Benchmark MEDIUM
CoMAI: A Collaborative Multi-Agent Framework for Robust and Equitable Interview Evaluation
Gengxin Sun, Ruihao Yu, Liangyi Yin +3 more
Ensuring robust and fair interview assessment remains a key challenge in AI-driven evaluation. This paper presents CoMAI, a general-purpose...
Benchmark LOW
Mechanistic Origin of Moral Indifference in Language Models
Lingyu Li, Yan Teng, Yingchun Wang
Existing behavioral alignment techniques for Large Language Models (LLMs) often neglect the discrepancy between surface compliance and internal...
Benchmark LOW
Context-Length Robustness in Question Answering Models: A Comparative Empirical Study
Trishita Dhara, Siddhesh Sheth
Large language models are increasingly deployed in settings where relevant information is embedded within long and noisy contexts. Despite this,...
Benchmark LOW
Evasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents
Simone Aonzo, Merve Sahin, Aurélien Francillon +1 more
Artificial intelligence (AI) systems are increasingly adopted as tool-using agents that can plan, observe their environment, and take actions over...
Benchmark LOW
CLAG: Adaptive Memory Organization via Agent-Driven Clustering for Small Language Model Agents
Taeyun Roh, Wonjune Jang, Junha Jung +1 more
Large language model agents heavily rely on external memory to support knowledge reuse and complex reasoning tasks. Yet most memory systems store...
Benchmark MEDIUM
SFCoT: Safer Chain-of-Thought via Active Safety Evaluation and Calibration
Yu Pan, Wenlong Yu, Tiejun Wu +4 more
Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks. However, they remain highly susceptible to...
Benchmark MEDIUM
Directional Embedding Smoothing for Robust Vision Language Models
Ye Wang, Jing Liu, Toshiaki Koike-Akino
The safety and reliability of vision-language models (VLMs) are a crucial part of deploying trustworthy agentic AI systems. However, VLMs remain...
Benchmark MEDIUM
SCAN: Sparse Circuit Anchor Interpretable Neuron for Lifelong Knowledge Editing
Yuhuan Liu, Haitian Zhong, Xinyuan Xia +3 more
Large Language Models (LLMs) often suffer from catastrophic forgetting and collapse during sequential knowledge editing. This vulnerability stems...
Benchmark MEDIUM
Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI
Jinhu Qi, Yifan Li, Minghao Zhao +4 more
As agentic AI systems move beyond static question answering into open-ended, tool-augmented, and multi-step real-world workflows, their increased...
Benchmark HIGH
When Scanners Lie: Evaluator Instability in LLM Red-Teaming
Lidor Erez, Omer Hofman, Tamir Nizri +1 more
Automated LLM vulnerability scanners are increasingly used to assess security risks by measuring different attack type success rates (ASR). Yet the...
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