AI Threat AlertAttackMEDIUM
SMCP: Secure Model Context Protocol
Xinyi Hou, Shenao Wang, Yifan Zhang +4 more
Agentic AI systems built around large language models (LLMs) are moving away from closed, single-model frameworks and toward open ecosystems that...
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 2881–2900 of 4,319 papers
AttackHIGH
Toward Universal and Transferable Jailbreak Attacks on Vision-Language Models
Kaiyuan Cui, Yige Li, Yutao Wu +4 more
Vision-language models (VLMs) extend large language models (LLMs) with vision encoders, enabling text generation conditioned on both images and text....
ToolLOW
HERMES: A Holistic End-to-End Risk-Aware Multimodal Embodied System with Vision-Language Models for Long-Tail Autonomous Driving
Weizhe Tang, Junwei You, Jiaxi Liu +5 more
End-to-end autonomous driving models increasingly benefit from large vision--language models for semantic understanding, yet ensuring safe and...
AttackHIGH
GradingAttack: Attacking Large Language Models Towards Short Answer Grading Ability
Xueyi Li, Zhuoneng Zhou, Zitao Liu +2 more
Large language models (LLMs) have demonstrated remarkable potential for automatic short answer grading (ASAG), significantly boosting student...
OtherLOW
Constitutional Spec-Driven Development: Enforcing Security by Construction in AI-Assisted Code Generation
Srinivas Rao Marri
The proliferation of AI-assisted "vibe coding" enables rapid software development but introduces significant security risks, as Large Language Models...
AttackMEDIUM
Unifying Adversarial Robustness and Training Across Text Scoring Models
Manveer Singh Tamber, Hosna Oyarhoseini, Jimmy Lin
Research on adversarial robustness in language models is currently fragmented across applications and attacks, obscuring shared vulnerabilities. In...
AttackHIGH
A Causal Perspective for Enhancing Jailbreak Attack and Defense
Licheng Pan, Yunsheng Lu, Jiexi Liu +5 more
Uncovering the mechanisms behind "jailbreaks" in large language models (LLMs) is crucial for enhancing their safety and reliability, yet these...
DefenseLOW
Engineering AI Agents for Clinical Workflows: A Case Study in Architecture,MLOps, and Governance
Cláudio Lúcio do Val Lopes, João Marcus Pitta, Fabiano Belém +2 more
The integration of Artificial Intelligence (AI) into clinical settings presents a software engineering challenge, demanding a shift from isolated...
AttackHIGH
Bypassing Prompt Injection Detectors through Evasive Injections
Md Jahedur Rahman, Ihsen Alouani
Large language models (LLMs) are increasingly used in interactive and retrieval-augmented systems, but they remain vulnerable to task drift;...
OtherLOW
Spectral Imbalance Causes Forgetting in Low-Rank Continual Adaptation
Hao Gu, Mao-Lin Luo, Zi-Hao Zhou +3 more
Parameter-efficient continual learning aims to adapt pre-trained models to sequential tasks without forgetting previously acquired knowledge. Most...
DefenseLOW
From Detection to Prevention: Explaining Security-Critical Code to Avoid Vulnerabilities
Ranjith Krishnamurthy, Oshando Johnson, Goran Piskachev +1 more
Security vulnerabilities often arise unintentionally during development due to a lack of security expertise and code complexity. Traditional tools,...
AttackHIGH
Jailbreaking LLMs via Calibration
Yuxuan Lu, Yongkang Guo, Yuqing Kong
Safety alignment in Large Language Models (LLMs) often creates a systematic discrepancy between a model's aligned output and the underlying...
ToolHIGH
DECEIVE-AFC: Adversarial Claim Attacks against Search-Enabled LLM-based Fact-Checking Systems
Haoran Ou, Kangjie Chen, Gelei Deng +4 more
Fact-checking systems with search-enabled large language models (LLMs) have shown strong potential for verifying claims by dynamically retrieving...
ToolMEDIUM
When Agents "Misremember" Collectively: Exploring the Mandela Effect in LLM-based Multi-Agent Systems
Naen Xu, Hengyu An, Shuo Shi +7 more
Recent advancements in large language models (LLMs) have significantly enhanced the capabilities of collaborative multi-agent systems, enabling them...
AttackHIGH
Text is All You Need for Vision-Language Model Jailbreaking
Yihang Chen, Zhao Xu, Youyuan Jiang +2 more
Large Vision-Language Models (LVLMs) are increasingly equipped with robust safety safeguards to prevent responses to harmful or disallowed prompts....
DefenseMEDIUM
A Fragile Guardrail: Diffusion LLM's Safety Blessing and Its Failure Mode
Zeyuan He, Yupeng Chen, Lang Lin +7 more
Diffusion large language models (D-LLMs) offer an alternative to autoregressive LLMs (AR-LLMs) and have demonstrated advantages in generation...
AttackHIGH
"Someone Hid It": Query-Agnostic Black-Box Attacks on LLM-Based Retrieval
Jiate Li, Defu Cao, Li Li +8 more
Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense...
AttackHIGH
Optimal Transport-Guided Adversarial Attacks on Graph Neural Network-Based Bot Detection
Kunal Mukherjee, Zulfikar Alom, Tran Gia Bao Ngo +2 more
The rise of bot accounts on social media poses significant risks to public discourse. To address this threat, modern bot detectors increasingly rely...
SurveyHIGH
Semantics-Preserving Evasion of LLM Vulnerability Detectors
Luze Sun, Alina Oprea, Eric Wong
LLM-based vulnerability detectors are increasingly deployed in security-critical code review, yet their resilience to evasion under...
DefenseMEDIUM
Assessing Domain-Level Susceptibility to Emergent Misalignment from Narrow Finetuning
Abhishek Mishra, Mugilan Arulvanan, Reshma Ashok +3 more
Emergent misalignment poses risks to AI safety as language models are increasingly used for autonomous tasks. In this paper, we present a population...
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