AI Threat AlertToolMEDIUM
ILION: Deterministic Pre-Execution Safety Gates for Agentic AI Systems
Florin Adrian Chitan
The proliferation of autonomous AI agents capable of executing real-world actions - filesystem operations, API calls, database modifications,...
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 2601–2620 of 4,319 papers
AttackHIGH
Dark and Bright Side of Participatory Red-Teaming with Targets of Stereotyping for Eliciting Harmful Behaviors from Large Language Models
Sieun Kim, Yeeun Jo, Sungmin Na +5 more
Red-teaming, where adversarial prompts are crafted to expose harmful behaviors and assess risks, offers a dynamic approach to surfacing underlying...
SurveyMEDIUM
LLM Scalability Risk for Agentic-AI and Model Supply Chain Security
Kiarash Ahi, Vaibhav Agrawal, Saeed Valizadeh
Large Language Models (LLMs) & Generative AI are transforming cybersecurity, enabling both advanced defenses and new attacks. Organizations now use...
ToolMEDIUM
AMV-L: Lifecycle-Managed Agent Memory for Tail-Latency Control in Long-Running LLM Systems
Emmanuel Bamidele
Long-running LLM agents require persistent memory to preserve state across interactions, yet most deployed systems manage memory with age-based...
AttackHIGH
When Backdoors Go Beyond Triggers: Semantic Drift in Diffusion Models Under Encoder Attacks
Shenyang Chen, Liuwan Zhu
Standard evaluations of backdoor attacks on text-to-image (T2I) models primarily measure trigger activation and visual fidelity. We challenge this...
BenchmarkMEDIUM
LoMime: Query-Efficient Membership Inference using Model Extraction in Label-Only Settings
Abdullah Caglar Oksuz, Anisa Halimi, Erman Ayday
Membership inference attacks (MIAs) threaten the privacy of machine learning models by revealing whether a specific data point was used during...
DefenseMEDIUM
MANATEE: Inference-Time Lightweight Diffusion Based Safety Defense for LLMs
Chun Yan Ryan Kan, Tommy Tran, Vedant Yadav +4 more
Defending LLMs against adversarial jailbreak attacks remains an open challenge. Existing defenses rely on binary classifiers that fail when...
AttackHIGH
When Prompt Optimization Becomes Jailbreaking: Adaptive Red-Teaming of Large Language Models
Zafir Shamsi, Nikhil Chekuru, Zachary Guzman +1 more
Large Language Models (LLMs) are increasingly integrated into high-stakes applications, making robust safety guarantees a central practical and...
BenchmarkLOW
Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse
Martin Bertran, Riccardo Fogliato, Zhiwei Steven Wu
Empirical conclusions depend not only on data but on analytic decisions made throughout the research process. Many-analyst studies have quantified...
BenchmarkHIGH
FENCE: A Financial and Multimodal Jailbreak Detection Dataset
Mirae Kim, Seonghun Jeong, Youngjun Kwak
Jailbreaking poses a significant risk to the deployment of Large Language Models (LLMs) and Vision Language Models (VLMs). VLMs are particularly...
BenchmarkLOW
Do Large Language Models Possess a Theory of Mind? A Comparative Evaluation Using the Strange Stories Paradigm
Anna Babarczy, Andras Lukacs, Peter Vedres +1 more
The study explores whether current Large Language Models (LLMs) exhibit Theory of Mind (ToM) capabilities -- specifically, the ability to infer...
AttackMEDIUM
AndroWasm: an Empirical Study on Android Malware Obfuscation through WebAssembly
Diego Soi, Silvia Lucia Sanna, Lorenzo Pisu +2 more
In recent years, stealthy Android malware has increasingly adopted sophisticated techniques to bypass automatic detection mechanisms and harden...
ToolHIGH
PenTiDef: Enhancing Privacy and Robustness in Decentralized Federated Intrusion Detection Systems against Poisoning Attacks
Phan The Duy, Nghi Hoang Khoa, Nguyen Tran Anh Quan +3 more
The increasing deployment of Federated Learning (FL) in Intrusion Detection Systems (IDS) introduces new challenges related to data privacy,...
DefenseLOW
Mining Type Constructs Using Patterns in AI-Generated Code
Imgyeong Lee, Tayyib Ul Hassan, Abram Hindle
Artificial Intelligence (AI) increasingly automates various parts of the software development tasks. Although AI has enhanced the productivity of...
AttackHIGH
TFL: Targeted Bit-Flip Attack on Large Language Model
Jingkai Guo, Chaitali Chakrabarti, Deliang Fan
Large language models (LLMs) are increasingly deployed in safety and security critical applications, raising concerns about their robustness to model...
AttackHIGH
Trojan Horses in Recruiting: A Red-Teaming Case Study on Indirect Prompt Injection in Standard vs. Reasoning Models
Manuel Wirth
As Large Language Models (LLMs) are increasingly integrated into automated decision-making pipelines, specifically within Human Resources (HR), the...
BenchmarkMEDIUM
Asking Forever: Universal Activations Behind Turn Amplification in Conversational LLMs
Zachary Coalson, Bo Fang, Sanghyun Hong
Multi-turn interaction length is a dominant factor in the operational costs of conversational LLMs. In this work, we present a new failure mode in...
ToolLOW
The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems
Leon Staufer, Kevin Feng, Kevin Wei +6 more
Agentic AI systems are increasingly capable of performing professional and personal tasks with limited human involvement. However, tracking these...
BenchmarkMEDIUM
What Makes a Good LLM Agent for Real-world Penetration Testing?
Gelei Deng, Yi Liu, Yuekang Li +5 more
LLM-based agents show promise for automating penetration testing, yet reported performance varies widely across systems and benchmarks. We analyze 28...
AttackLOW
Jolt Atlas: Verifiable Inference via Lookup Arguments in Zero Knowledge
Wyatt Benno, Alberto Centelles, Antoine Douchet +1 more
We present Jolt Atlas, a zero-knowledge machine learning (zkML) framework that extends the Jolt proving system to model inference. Unlike zkVMs...
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