AI Threat AlertAttackMEDIUM
HoneyRoute: Honeypot-Model Routing for Adversarial LLM Serving
Han Jin
We introduce HoneyRoute, an inference-serving layer that detects whether an incoming request is malicious and, if so, routes it to a dedicated...
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 281–300 of 685 papers
Clear filtersAttackHIGH
ACEA: An Adversarial Co-Evolution Arena for Head-to-Head Red-Team and Blue-Team LLM Testing
Yi Ting Shen, Kentaroh Toyoda, Alex Leung
Automated red-team attacks and blue-team defenses for large language models (LLMs) are advancing quickly. However, attackers and defenders are built...
AttackMEDIUM
LLM-Based Penetration Testing in the Presence of Honeypots
Xinhong Xie, Piyush Nagasubramaniam, Neeraj Karamchandani +1 more
Large language model (LLM) agents are increasingly employed for offensive cybersecurity tasks such as automated vulnerability discovery,...
AttackHIGH
CoRL: Co-Evolutionary Reinforcement Learning for Adaptive Indirect Prompt-Injection Attacks and Defenses
Boyang Zhang, Qingxin Xiao, Lingwei Dang +1 more
Tool-augmented language agents are vulnerable to indirect prompt injection (IPI). Unlike direct prompt injection, IPI hides adversarial instructions...
AttackHIGH
CrACK: Adversarial Attacks on Cross-Model Consistency in Collaborative Vision Foundation Models
Feifei Liu, Jintao Cheng, Chi Man Vong +1 more
Training-free collaborative pipelines that integrate Vision Foundation Models such as CLIP, SAM, and DINO achieve strong open-vocabulary dense...
AttackHIGH
Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration Testing
Weizhe Wang, Yitong Zhang, Yao Zhang +4 more
Large language model (LLM) based agents are increasingly applied to cybersecurity tasks such as vulnerability discovery and automated penetration...
AttackMEDIUM
Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood Collaboration
Xiao Ma, Hong Shen, Hui Tian +2 more
This paper proposes a robust decentralized personalized federated learning method R-DPFL, that enables clients to reduce the impact of Byzantine...
AttackMEDIUM
Towards a Resilience-Theoretic Foundation for Adversarial Robustness in Industrial Control System Anomaly Detection
Branka Stojanović, Andreas Flatscher, Michael Somma
Anomaly-based intrusion detection systems in industrial control systems (ICS) and operational technology (OT) environments are increasingly required...
AttackHIGH
Shifting from Injection to Interaction: Rethinking Web Security in the Age of LLMs and Beyond
Nivedita Singh, Alsharif Abuadbba, Yansong Gao +2 more
Large language models (LLMs) are becoming integral to web applications and browser agents, transforming online interactions while introducing new...
AttackHIGH
A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious Behaviors
Pengxun Li, Litian Zhang, Jianwei Hou +4 more
Modern AI agent harnesses expose lifecycle hooks that bind shell commands to runtime events such as session start, tool calls, and file edits. These...
AttackHIGH
IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks
Saikat Mondal, Mamta, Deeksha Varshney +2 more
Large language models (LLMs) are increasingly used in multilingual settings, yet their safety is still evaluated primarily in English. This limits...
AttackHIGH
AlcaTRAz - Anchored Tree-Rule Defense Against Jailbreaks
Jakub Reš, Petr Kaška, Martin Perešíni +2 more
Large language models (LLMs) are vulnerable to jailbreak attacks that bypass safety alignment through carefully crafted prompts. Many existing...
AttackMEDIUM
Trust Me, I'm Your Developer: Self-Issued Authentication in Large Language Models
Syed Ghazanfar Abbas, Dongyan Xu
Large language model (LLM) security has largely focused on role-playing jailbreaks, with less attention to what happens when a user asks an LLM to...
AttackLOW
Population-Calibrated Graph Screening at 835-Million-Address Scale, with Label-Free Transfer to New Chains
Yury Korolev
Compliance screening of blockchain addresses is, in practice, a lookup against sanctions registries plus clustering heuristics; it fails on...
AttackHIGH
CodePoisonRAG: Knowledge Poisoning Attacks on Retrieval-Augmented Code Generation
Varun Gadey, Ziad Marey, Alexandra Dmitrienko
Retrieval-Augmented Code Generation (RACG) improves LLM-based software development by retrieving external code artifacts, documentation, and patches,...
AttackHIGH
Automated Vulnerability Injection in Smart Contracts Using Large Language Models
Luca Migliaccio, Roberto Natella, Naghmeh Ivaki +2 more
Assessing vulnerability detection tools for smart contracts requires datasets with known ground truth, yet such datasets are scarce and difficult to...
AttackMEDIUM
A Finger on the Scale: Covert Policy Steering through Agentic Skills
Jiarui Li, Jiahao Chen, Chunyi Zhou +5 more
Reusable agent skills extend large language model (LLM) agents with task procedures, tool-use guidance, and output constraints. Yet these skills also...
AttackHIGH
Poisoning Attacks on the PGM-index
Atsuki Sato, Martin Aumüller, Yusuke Matsui
The PGM-index (Ferragina and Vinciguerra, VLDB'20) is one of the most practical learned indexes, owing to its theoretical elegance and consistently...
AttackHIGH
InfraPatch: Cross-Task Targeted Grayscale Patch Attacks on Infrared-Adapted Vision-Language Models
Chengyin Hu, Dingyi Lu, Jiaju Han +5 more
Infrared vision-language models (IR-VLMs) have emerged as a promising paradigm for multimodal perception under low-visibility conditions, yet their...
AttackMEDIUM
WeaveMark: Robust and Scalable Multi-bit LLM Watermarking via Coded Payload Spreading
Gang-Hyun Park, Ju-Hyeong Lee, Hee-Youl Kwak +1 more
Multi-bit watermarking for large language models (LLMs) enables content source tracing by embedding user-identifiable messages into generated text....
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