AI Threat Alert
Attack MEDIUM
Walking on the DARKSIDE
Aldo Gangemi, Emanuele Bottazzi
Large Language Models (LLMs) recognise patterns but do not natively track the path of exclusions that a coherent discourse demands. When an input...
AI Security Research
AI Threat Alert indexes 3,771+ 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
- Total3,771
- Attack1,458
- Benchmark1,072
- Defense533
- Tool380
- Survey220
Showing 301–320 of 3,771 papers
Attack MEDIUM
Breakout/Interchange Reconnection as a driver of Jets, Fast CME, and Solar Energetic Particles
Pankaj Kumar, Judith T. Karpen, David Lario +4 more
Understanding how energetic particles are accelerated and released from the low corona into the interplanetary medium during solar eruptions is...
Benchmark LOW
Hidden in the Request: Explaining Unethical LLM Compliance through Token Relevance
Or Biton, Tomer Krichli, Itai Allouche +1 more
Although Large Language Models (LLMs) are aligned to optimize for both helpfulness and harmlessness, these dual objectives may conflict, inevitably...
Benchmark MEDIUM
Towards Automated Cyber Threat Intelligence Elicitation in Underground Forums
Lorenzo Bossi, Federico Saccani, Francesco Panebianco +4 more
Cyber threat intelligence from underground forums has traditionally relied on passive monitoring. However, as users have become more aware of...
Other MEDIUM
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
Jian Yang, Haau-Sing Li, Shawn Guo +8 more
As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention,...
Other MEDIUM
CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild
Jian Yang, Haau-Sing Li, Shawn Guo +9 more
As large language models (LLMs) continue to advance in coding capabilities, their potential in cybersecurity has drawn increasing research attention,...
Benchmark LOW
From Inertia to Objectivity: Improving Deep Research Agents with Noise Isolation
Xiangxin Zhang, Zhanwei Zhang, Zhihang Fu +2 more
Web search agents powered by Large Language Models (LLMs) show strong promise, but deep research tasks expose a recurring failure mode: once an agent...
Attack HIGH
PsychJail: Exploring Psychological Jailbreaks via Multi-Turn Persuasion of LLM Policies
Zeyu Feng, Qingyu Wu, Yuzhe Luo +1 more
Large language models (LLMs) are increasingly deployed in education, healthcare, policy advising, and other interactive settings, where users engage...
Defense MEDIUM
Verification-Guided Specification Synthesis with Large Language Models for Intrusion Detection Rules
Kohei Yamamoto, Marie Katsurai
Attacks against Internet-connected IoT devices continue to increase; however, transforming observed attack traffic into deployable intrusion...
Tool MEDIUM
AgentFlow: A Flow-Centric Policy Language and Framework for Securing LLM Agent Systems
Basavesh Ammanaghatta Shivakumar, Swarn Priya, Peng Gao
LLM agents increasingly read untrusted content, invoke external tools, access private data, and delegate work to other agents. Harm often arises not...
Benchmark LOW
The Compaction Cliff in Long-Running AI Agent Memory
Saber Zerhoudi, Jelena Mitrovic, Michael Granitzer
A safety rule and an episodic log compete for the same tokens in an AI agent's context. When the budget overflows, both are summarized at the same...
Survey LOW
EGAMA-RC: Risk-Calibrated Evidence-Gated Adaptive Malware Analysis for Robust and Interpretable Memory-Forensic Triage
Isaac Kofi Nti
Machine-learning malware detectors often achieve high clean-data accuracy, but operational triage also requires evidence about uncertainty, novelty,...
Attack MEDIUM
Model-Consistent Byzantine-Resilient Decentralized Federated Learning for Collaborative Missions
Yue Li, Sudip Bhujel, Cameron Lira +2 more
Decentralized federated learning (DFL) is a promising paradigm for autonomous nodes to collaboratively train AI models without relying on a central...
Benchmark LOW
ClawProBench: Trace-Aware Evaluation of AI Agents with Runtime Coverage and Frozen Workplace-Style Holdouts
YuanHang Xiao
Agent benchmarks often evaluate only final answers even when agents run on stateful runtimes. We argue this under-specifies what is being evaluated:...
Attack HIGH
Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language Models
Wenyun Li, Guiping Cao, Xiangyuan Lan +1 more
Multimodal Large Language Models (MLLMs) have achieved remarkable progress in vision-language interaction, yet their safety alignment remains...
Benchmark LOW
Phantom Gains: Auditing Self-Improvement Against a Measured Null
Cheng Xu, Nan Yan, Liming Chen +1 more
Whether a language model has improved itself is increasingly judged not by mean accuracy but by which individual problems it gains and loses....
Attack MEDIUM
QUASAR: A Quantum-Classical Neural Network for SAR Satellite Physical-Layer Authentication
Vincenzo Sammartino, Nathanael Denis, Roberto Di Pietro
X-band SAR satellites (8-12 GHz) play a critical role in disaster response, environmental monitoring, and military intelligence. Yet, they lack...
Benchmark MEDIUM
EchoCoT: Extracting Hidden Chain-of-Thought from Large Reasoning Models
Yiting Qu, Ziqing Yang, Chi Cui +3 more
Hidden chain-of-thought (CoT) traces, especially those from frontier proprietary large reasoning models (LRMs), are valuable model assets. Yet...
Attack HIGH
COPA: Continual Preference Optimization for Adaptive Prompt Injection Defense
Roshan Sood, Onat Gungor, Tajana Rosing
LLMs remain vulnerable to prompt injection attacks, where adversarial instructions embedded in user inputs or external content manipulate model...
Benchmark MEDIUM
MaliciousSkillBench: A Comprehensive Benchmark for Malicious Agent Skill Detection
Yue Wang, Yi Liu, Gelei Deng +4 more
Agent Skills extend LLM agents with reusable instruction packages that may also include scripts, resources, and service configuration. This creates a...
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 3,771+ 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