AI Threat Alert
Attack MEDIUM
aiAuthZ: Off-Host, Identity-Bound Authorization for AI Agents
Sai Varun Kodathala
AI agents issue tool calls on the basis of text they cannot verify, so any party who controls part of the context can forge the appearance of...
AI Security Research
AI Threat Alert indexes 3,397+ 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
- Total3,397
- Attack1,314
- Benchmark975
- Defense477
- Tool341
- Survey196
Showing 301–320 of 1,755 papers
Clear filters Benchmark MEDIUM
Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets
Paul K. Mandal, Pavan Reddy, Tristan Malatynski
Model-specific adversarial attacks have been extensively studied. We study a different failure mode: naturally occurring statistical signals in...
Attack MEDIUM
Untrusted Content Masking for Web Agents with Security Guarantees
Kristina Nikolić, Egor Zverev, Javier Rando +3 more
Defenses that provide security guarantees against prompt injection attacks rely on strict isolation between trusted instructions and untrusted data....
Attack LOW
Full-range Binary Classifier Calibration for Stable Model Updates in Production
Konstantin Berlin
Detection models running in adversarial environments face a malicious distribution that drifts rapidly while the benign distribution stays...
Attack HIGH
When Claws Remember but Do Not Tell: Stealthy Memory Injection in Persistent Personal Agents
Yechao Zhang, Shiqian Zhao, Jiawen Zhang +5 more
Persistent personal agents combine long-term memory with access to users' external environments, enabling personalized foreground assistance and...
Attack HIGH
Agent Data Injection Attacks are Realistic Threats to AI Agents
Woohyuk Choi, Juhee Kim, Taehyun Kang +3 more
AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security...
Attack HIGH
Your Agent's Memories Are Not Its Own: Forged Reasoning Attacks on LLM Agent Memory and Defenses
Neeraj Karamchandani, Piyush Nagasubramaniam, Sencun Zhu +1 more
Persistent memory has enabled large language model (LLM) agents to store factual knowledge, prior decisions, reasoning histories, tool usage...
Attack LOW
TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction
Mouhamed Amine Bouchiha, Gregory Blanc
Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated...
Attack LOW
TACTIC-KG: Toward Small Agent Teams for Cyber Threat Intelligence Knowledge Graph Construction
Mouhamed Amine Bouchiha, Gregory Blanc
Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated...
Defense MEDIUM
ShadowProbe: Language-Extensible Detection of Hidden Algorithmic Complexity Vulnerabilities
Yuanmin Xie, Xiangfan Wu, Wenhao Wu +6 more
Algorithmic Complexity Vulnerabilities (ACVs) arise when adversarial inputs trigger worst-case execution behavior, causing severe performance...
Defense MEDIUM
Retroactive Chain-of-Thought (RetroCoT): Forensic Reconstruction Prompts as a Safety Diagnostic Across Model Generations
Samira Hajizadeh
Safety alignment in large language models is typically evaluated against direct, imperative harmful requests. We show that this alignment is highly...
Tool HIGH
Knowledge Base Poisoning Attacks and Defense for Policy-Aware LLM-RAG Framework
Om Solanki, Lopamudra Praharaj, Deepti Gupta +1 more
This paper presents an adversarial security study of the Policy-Aware LLM Retrieval-Augmented Generation (PA-LLM-RAG) framework for Internet of...
Benchmark MEDIUM
Biological Motifs for Agentic Control
Bogdan Banu
The transition of Large Language Models (LLMs) from passive generators to autonomous agents has introduced significant challenges in reliability,...
Benchmark MEDIUM
Unsupervised Features Mining via Activation Geometry
Amit LeVi, Elad David, Max Fomin
Interpretability methods aim to reveal the features represented inside large language models (LLMs). Many existing methods begin with labeled...
Benchmark LOW
CoCoScale: Leveraging Layer-wise Scaling to Unlock the Potential of Online LLM Serving
Jingfeng Wu, Yiyuan He, Minxian Xu +7 more
Online large language model (LLM) serving has become the backbone of modern AI applications, powering diverse downstream services through shared...
Attack HIGH
Distributed Attacks in Persistent-State AI Control
Josh Hills, Ida Caspary, Asa Cooper Stickland
As AI coding agents become more autonomous, they increasingly ship code iteratively, with the codebase persisting across sessions. This persistence...
Defense MEDIUM
Online Safety Monitoring for LLMs
Mona Schirmer, Metod Jazbec, Alexander Timans +3 more
Despite alignment training, LLMs remain prone to generating unsafe outputs at deployment time. Monitoring outputs online and raising an alarm when...
Attack HIGH
Towards Robustness against Typographic Attack with Training-free Concept Localization
Bohan Liu, Wenqian Ye, Guangzhi Xiong +3 more
Models trained via Contrastive Language-Image Pretraining (CLIP) serve as the foundational vision encoders for most modern Large Vision Language...
Defense MEDIUM
Cloak and Detonate: Scanner Evasion and Dynamic Detection of Agent Skill Malware
Zimo Ji, Congying Xu, Zongjie Li +4 more
LLM coding agents increasingly rely on third-party agent skills from public marketplaces, which execute with the agent's privileges and create a...
Benchmark LOW
Copewell: A Multi-Agent Swarm Architecture for Equitable Mental Wellness Support
Seren Yenikent, Jack Vinijtrongjit, Katherine Ng
Mental health disorders affect nearly one billion people globally, yet 75% of individuals in low- and middle-income countries receive no treatment...
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 3,397+ 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