AI Threat AlertBenchmarkMEDIUM
Human-on-the-Bridge: Scalable Evaluation for AI Agents
Fouad Bousetouane
AI agents must be evaluated as behavioral systems, not as isolated response generators. They reason across turns, call tools, preserve context,...
AI Security Research
AI Threat Alert indexes 4,319+ peer-reviewed and preprint papers on AI/ML security — covering adversarial attacks, model defenses, red-teaming benchmarks, surveys, and security tooling. Papers are sourced from arXiv, classified by type and by relevance to real-world threats, and cross-referenced with the CVEs and incidents they relate to.
- Adversarial attacks
- Model defenses
- Red-teaming benchmarks
- Surveys
- Security tooling
- Total4,319
- Attack1,676
- Benchmark1,229
- Defense610
- Tool432
- Survey252
Showing 241–260 of 735 papers
Clear filtersBenchmarkMEDIUM
The Art of Mixology: Mixup-based Obfuscation for Privacy-Preserving Split Learning in Large Language Models
Chen Chen, Xiang Gao, Xianshun Wang +6 more
Split learning provides a practical paradigm for resource-constrained users to train Large Language Models (LLMs) by offloading computation-intensive...
BenchmarkMEDIUM
Robust and Automated Reconfiguration of Byzantine Wide-Area Replication
Rowdy Chotkan, Bulat Nasrulin, Johan Pouwelse +1 more
Distributed systems handle adversarial nodes through redundancy, which imposes a significant performance overhead. In blockchain systems, Byzantine...
BenchmarkMEDIUM
An Evaluation of Data Leakage Risks in Tool-Using LLM Agents in Realistic Scenarios
Hankyul Baek, Jaewon Noh, Sang Seo +5 more
AI agents are increasingly being adopted in enterprise and personal settings with access to emails, databases, documents, and other tools where they...
BenchmarkMEDIUM
Your "Pro" LLM Subscription May Actually Be "Free": Exposing Fingerprint Spoofing Risks in LLM Inference Services
Jiahao Zhang, Xiuyu Li, Suhang Wang
As Large Language Model (LLM) APIs become ubiquitous, users increasingly rely on black-box fingerprinting to verify that providers are serving the...
BenchmarkMEDIUM
SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills
Ismail Hossain, Sai Puppala, Md Jahangir Alam +2 more
Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent...
BenchmarkMEDIUM
Prefill Awareness in Large Language Models
Andy Wang, Parv Mahajan, David Demitri Africa +3 more
Safety-relevant studies of language models, including alignment and jailbreaking evaluations and AI control protocols, often rely on prefilling model...
BenchmarkMEDIUM
Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows
Timothy McAllister, Sina Abdidizaji, Ivan Garibay +1 more
As LLM-based multi-agent systems (MAS) are deployed in the wild, the resilience of their collaboration structures against adversarial compromise...
BenchmarkMEDIUM
Fed-FBD: Federated Functional Block Diversification for Isolation, Privacy, and Surgical Unlearning
Weijie Chen, Alan B. McMillan
Federated learning (FL) enables collaborative model training without sharing raw patient data, but standard approaches such as FedAvg treat each...
BenchmarkMEDIUM
OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents
Jin Xie, Songze Li
Large language model (LLM) agents increasingly act on a user's behalf -- reading personal files, calling tools, transacting with external services --...
BenchmarkMEDIUM
Mind your key: An Empirical Study of LLM API Credential Leakage in iOS Apps
Pinran Gao, Lingxiang Wang, Ying Zhang +1 more
The rapid integration of large language models (LLMs) into mobile applications has introduced a new class of credential security risk: leaked...
BenchmarkMEDIUM
Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language Models
Malikeh Ehghaghi, Boglárka Ecsedi, Marsha Chechik +1 more
Adversarial robustness evaluations of large language models (LLMs) typically report attack success rate (ASR) under fixed query budgets, implicitly...
BenchmarkMEDIUM
It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO
Naihao Deng, Yilun Zhu, Naichen Shi +2 more
Warning: This paper contains several toxic and offensive statements. Modern large language models (LLMs) are typically aligned through large-scale...
BenchmarkMEDIUM
AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environments
Peiyang Li, Songping Wang, Yi Huang +9 more
Autonomous AI agents have driven the transition from conversation to task execution, shifting security failures from textual deception to system...
BenchmarkMEDIUM
Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMs
Saeid Jamshidi, Amin Nikanjam, Arghavan Moradi Dakhel +2 more
Large Language Models (LLMs) in multi-turn interactions maintain evolving context rather than generating isolated responses, making them vulnerable...
BenchmarkMEDIUM
Baseline-Free Policy Optimization for Neural Combinatorial Optimization
Carlos S. Sepúlveda, Gonzalo A. Ruz
Neural combinatorial optimization (NCO) trains autoregressive policies to solve routing problems. The standard training algorithm, REINFORCE with a...
BenchmarkMEDIUM
Safe-RULE: Safe Reinforcement UnLEarning
Shixiong Jiang, Taozheng Zhu, Fanxin Kong
Offline safe reinforcement learning (Safe RL) enables policy learning without online interactions, making it suitable for safety-critical systems...
BenchmarkMEDIUM
AI Scientists Are Only as Good as Their Evidence: A Stratified Ablation of Proprietary Data and Reasoning Skills in Drug-Asset Valuation
Yinan Wang
AI Scientist agents are often evaluated as if capability were mainly a function of model quality, prompting, or reasoning scaffolds. We test a...
BenchmarkMEDIUM
Targeting World Models to Compromise Robot Learning Pipelines
Ethan Rathbun, Ahmed Agha, Saaduddin Mahmud +3 more
World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training...
BenchmarkMEDIUM
Can Data Work be Reparative?
Srravya Chandhiramowuli, Ding Wang, Alex Taylor
We present an ethnographic study of an alternative approach to data work, developed by a civic-tech initiative that builds datasets for training and...
Frequently asked questions
What is AI security research?
AI security research studies how AI and machine-learning systems can be attacked and defended — covering adversarial examples, prompt injection, model poisoning, training-data extraction, and the mitigations against them. AI Threat Alert curates this research from academic sources so security teams can track the threats behind emerging AI risks.
How many AI security papers does AI Threat Alert track?
AI Threat Alert indexes 4,319+ papers on AI/ML security, classified across attack, defense, benchmark, survey, and tool categories and updated continuously.
Where do the research papers come from?
Papers are sourced from arXiv, then classified by type and by relevance to real-world AI/ML threats, and cross-referenced with the CVEs and incidents they relate to.
What topics does the AI security research cover?
Coverage spans adversarial attacks, model and system defenses, red-teaming benchmarks, literature surveys, and security tooling for LLMs, ML libraries, AI agents, and inference pipelines.
How is this different from a generic paper search?
Every paper is filtered for AI security relevance and linked to the vulnerabilities, vendors, and incidents it relates to, so the research connects directly to operational threat intelligence.
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