AI Threat Alert
Defense LOW
Multi-Agent AI Safety as an Institutional Design Problem
Abdullah X
AI agents increasingly work inside systems that govern how they delegate tasks, move information, execute actions, and use shared resources. Recent...
AI Security Research
AI Threat Alert indexes 3,371+ 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
- Total3,371
- Attack1,303
- Benchmark970
- Defense471
- Tool340
- Survey195
Showing 1–20 of 471 papers
Clear filters Defense MEDIUM
LLM Reasoning for Subjective Tasks: Failure Modes, Mitigation, and Dynamic Reasoning Routing
Juncheng Dong, Ding Tong, Ishan Gupta +1 more
Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a matter of subjective human preference. As...
Defense LOW
A Dynamic-Semantics Framework for Grounding Human Referring Expressions in Visual Perceptual Data
Joseph Bingham
Humans converge on shared names for novel, hard-to-describe objects through repeated interaction, a process psycholinguists call lexical entrainment....
Defense LOW
Resourced Authority A Mechanism-Design Model for Participatory Governance of Deployed AI Agents
Praphul Chandra, Sujit Gujar, Ganesh Ghalme
We give a formal mechanism design model for the continuous participatory governance of a deployed AI agent. The mechanism is built on the principle...
Defense MEDIUM
ECHO: A Locally-Deployable Agentic Health Assistant with Temporal Memory, Safety Guardrails, and Speech Assessment
Abdulkadir Külçe, Alihan Esen, Cağla Fikir +4 more
This paper presents ECHO (Enhanced Care \& Health Observer), a locally-deployable conversational health assistant for long-term chronic care...
Defense MEDIUM
Robust Context-Aware Detection of Malicious Instructions in Text
Buzhao Liu, Xinhang Ma, Yevgeniy Vorobeychik
The remarkable instruction-following ability of modern LLMs has enabled their practical use as the minds of agents that can autonomously complete...
Defense MEDIUM
Mood Matters: How Syntactic Sensitivity Undermines Safety Alignment
Alina Klerings, Jannik Brinkmann, Heiner Stuckenschmidt +1 more
Large language models typically undergo post-training to align them with safety policies but there exist many sophisticated jailbreaks that sidestep...
Defense MEDIUM
LLM-Assisted Detection and Repair of Hardware Security Vulnerabilities in Verilog Designs
Ethen Santana, Gabriel Gyaase, Hao Zheng
Hardware designs, like software, are susceptible to bugs that can introduce security vulnerabilities and create opportunities for malicious...
Defense MEDIUM
Trident : How to Break Deep Reinforcement Learning Cyber Defenses (Agentic)
Ryozo Masukawa, Ian Bryant, Armita Kazeminajafabadi +6 more
Autonomous cyber defense systems based on Deep Reinforcement Learning (DRL) have attracted significant research attention, yet remain evaluated...
Defense HIGH
LLM-based Vulnerability Discovery in Business Process Documentation
Ben Falchuk, Himanshu Garg, Euthimios Panagos +1 more
Just like software and hardware, business processes are susceptible to vulnerabilities that can lead to product quality issues, delays, and increased...
Defense LOW
A game theory for foundation models shows new paths to rational cooperation through similarity inference
Alexander Meulemans, Maciej Wołczyk, Marissa A. Weis +11 more
As autonomous agents powered by foundation models are increasingly integrated into social and economic systems, understanding the principles...
Defense MEDIUM
SkillSentry: Adaptive Honey Worlds for Dynamic Safety Testing of Agent Skills
Nizhang Li, Zonghao Ying, Xiangfan Wu +7 more
External skills extend the capabilities of large language model agents, but also introduce an execution-time attack surface: a skill that appears...
Defense MEDIUM
When Modalities Fail to Tango: Conformal Backdoor Detection in Multimodal Contrastive Learning
Yiming Chen, Kemou Li, Haiwei Wu +1 more
Backdoor attacks in multimodal contrastive learning (MCL) have garnered growing attention in recent years, as many downstream tasks critically depend...
Defense MEDIUM
The Evolutionary Origin of Values: implications for AI alignment, sentience and existential risk
Francis Heylighen
AI systems based on Large Language Models (LLMs) have prompted fears that they may harbor hidden goals, seek to dominate or eliminate humanity, or...
Defense HIGH
CLEAR: Causal Context-Based Agentic Reasoning for Vulnerability Detection
Sungju Yun, Sijune Hwang, Yeonjoon Lee +2 more
Detecting source code vulnerabilities is increasingly difficult as modern security flaws are rooted in complex causal dependencies between execution...
Defense HIGH
EntailLLM: Verifying LLM-Generated Vulnerability Discovery Paths with Domain Knowledge via Logic Programming
Kaustuv Mukherji, Jaikrishna Manojkumar Patil, Colton Payne +4 more
Large language models are increasingly used to reason about software vulnerabilities, but their outputs can silently violate domain knowledge,...
Defense MEDIUM
Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs
Pingyu Wu, Lingyao Zhu, Weiming Zhang +1 more
Large language model safeguards decide whether to answer before seeing how an answer will be used. This creates a basic problem for dual-use tasks:...
Defense MEDIUM
A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models
Xiangyu Yin, Tora Bodin, Rohan Menon +1 more
Inference time defences against vision language model jailbreaks often subtract a calibrated direction from the residual stream at a chosen decoder...
Defense MEDIUM
On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment
Yongjian Guo, Wanlun Ma, Lingyu Shen +2 more
Fine-tuning is the dominant paradigm for specializing large language models (LLMs), yet it exposes a critical vulnerability: malicious data providers...
Defense MEDIUM
SkillGate: Cost Efficient Runtime Malicious Skill File Detection in Coding Agents
Rui Yang, Michael Fu, Kla Tantithamthavorn +2 more
Software engineering teams now deploy AI coding agents (Cursor, Claude Code, GitHub Copilot) as first-class productivity tools, installing...
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 3,371+ 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