AI Threat AlertDefenseLOW
Robust Reasoning as a Symmetry-Protected Topological Phase
Ilmo Sung
Large language models suffer from "hallucinations"-logical inconsistencies induced by semantic noise. We propose that current architectures operate...
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 3161–3180 of 4,319 papers
BenchmarkMEDIUM
From Understanding to Engagement: Personalized pharmacy Video Clips via Vision Language Models (VLMs)
Suyash Mishra, Qiang Li, Srikanth Patil +1 more
Vision Language Models (VLMs) are poised to revolutionize the digital transformation of pharmacyceutical industry by enabling intelligent, scalable,...
BenchmarkMEDIUM
Knowledge-to-Data: LLM-Driven Synthesis of Structured Network Traffic for Testbed-Free IDS Evaluation
Konstantinos E. Kampourakis, Vyron Kampourakis, Efstratios Chatzoglou +2 more
Realistic, large-scale, and well-labeled cybersecurity datasets are essential for training and evaluating Intrusion Detection Systems (IDS). However,...
AttackMEDIUM
Effects of personality steering on cooperative behavior in Large Language Model agents
Mizuki Sakai, Mizuki Yokoyama, Wakaba Tateishi +1 more
Large language models (LLMs) are increasingly used as autonomous agents in strategic and social interactions. Although recent studies suggest that...
ToolHIGH
Defense Against Indirect Prompt Injection via Tool Result Parsing
Qiang Yu, Xinran Cheng, Chuanyi Liu
As LLM agents transition from digital assistants to physical controllers in autonomous systems and robotics, they face an escalating threat from...
BenchmarkLOW
Tool-MAD: A Multi-Agent Debate Framework for Fact Verification with Diverse Tool Augmentation and Adaptive Retrieval
Seyeon Jeong, Yeonjun Choi, JongWook Kim +1 more
Large Language Models (LLMs) suffer from hallucinations and factual inaccuracies, especially in complex reasoning and fact verification tasks....
BenchmarkMEDIUM
StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation
Huawei Zheng, Xinqi Jiang, Sen Yang +3 more
Large language models (LLMs) are increasingly applied in specialized domains such as finance and healthcare, where they introduce unique safety...
DefenseMEDIUM
AM$^3$Safety: Towards Data Efficient Alignment of Multi-modal Multi-turn Safety for MLLMs
Han Zhu, Jiale Chen, Chengkun Cai +8 more
Multi-modal Large Language Models (MLLMs) are increasingly deployed in interactive applications. However, their safety vulnerabilities become...
ToolHIGH
Unified Framework for Qualifying Security Boundary of PUFs Against Machine Learning Attacks
Hongming Fei, Zilong Hu, Prosanta Gope +1 more
Physical Unclonable Functions (PUFs) serve as lightweight, hardware-intrinsic entropy sources widely deployed in IoT security applications. However,...
ToolMEDIUM
ResMAS: Resilience Optimization in LLM-based Multi-agent Systems
Zhilun Zhou, Zihan Liu, Jiahe Liu +5 more
Large Language Model-based Multi-Agent Systems (LLM-based MAS), where multiple LLM agents collaborate to solve complex tasks, have shown impressive...
AttackHIGH
Know Thy Enemy: Securing LLMs Against Prompt Injection via Diverse Data Synthesis and Instruction-Level Chain-of-Thought Learning
Zhiyuan Chang, Mingyang Li, Yuekai Huang +6 more
Large language model (LLM)-integrated applications have become increasingly prevalent, yet face critical security vulnerabilities from prompt...
AttackHIGH
Constitutional Classifiers++: Efficient Production-Grade Defenses against Universal Jailbreaks
Hoagy Cunningham, Jerry Wei, Zihan Wang +26 more
We introduce enhanced Constitutional Classifiers that deliver production-grade jailbreak robustness with dramatically reduced computational costs and...
SurveyMEDIUM
Autonomous Agents on Blockchains: Standards, Execution Models, and Trust Boundaries
Saad Alqithami
Advances in large language models have enabled agentic AI systems that can reason, plan, and interact with external tools to execute multi-step...
ToolHIGH
BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based Agents
Yunhao Feng, Yige Li, Yutao Wu +6 more
Large language model (LLM) agents execute tasks through multi-step workflows that combine planning, memory, and tool use. While this design enables...
AttackMEDIUM
Deep Dive into the Abuse of DL APIs To Create Malicious AI Models and How to Detect Them
Mohamed Nabeel, Oleksii Starov
According to Gartner, more than 70% of organizations will have integrated AI models into their workflows by the end of 2025. In order to reduce cost...
SurveyMEDIUM
A Survey of Agentic AI and Cybersecurity: Challenges, Opportunities and Use-case Prototypes
Sahaya Jestus Lazer, Kshitiz Aryal, Maanak Gupta +1 more
Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over...
BenchmarkLOW
TSSR: Two-Stage Swap-Reward-Driven Reinforcement Learning for Character-Level SMILES Generation
Jacob Ede Levine, Yun Lyan Luo, Sai Chandra Kosaraju
The design of reliable, valid, and diverse molecules is fundamental to modern drug discovery, as improved molecular generation supports efficient...
BenchmarkLOW
Rational Synthesizers or Heuristic Followers? Analyzing LLMs in RAG-based Question-Answering
Atharv Naphade
Retrieval-Augmented Generation (RAG) is the prevailing paradigm for grounding Large Language Models (LLMs), yet the mechanisms governing how models...
AttackMEDIUM
Merging Triggers, Breaking Backdoors: Defensive Poisoning for Instruction-Tuned Language Models
San Kim, Gary Geunbae Lee
Large Language Models (LLMs) have greatly advanced Natural Language Processing (NLP), particularly through instruction tuning, which enables broad...
AttackHIGH
Large Language Models for Detecting Cyberattacks on Smart Grid Protective Relays
Ahmad Mohammad Saber, Saeed Jafari, Zhengmao Ouyang +3 more
This paper presents a large language model (LLM)-based framework that adapts and fine-tunes compact LLMs for detecting cyberattacks on transformer...
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