AI Threat AlertBenchmarkMEDIUM
Context-to-Execution Integrity for LLM Agents
Igor Santos-Grueiro
Language-model agents read attacker-writable context to solve tasks. Tool execution needs a separate authority check for protected sink fields,...
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 661–680 of 2,152 papers
Clear filtersAttackMEDIUM
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...
BenchmarkMEDIUM
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...
AttackMEDIUM
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....
DefenseMEDIUM
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...
DefenseMEDIUM
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...
BenchmarkMEDIUM
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,...
BenchmarkMEDIUM
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...
DefenseMEDIUM
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...
DefenseMEDIUM
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...
AttackMEDIUM
Privacy-Preserving and Verifiable Approximate Distributed Coded Computing
Xavier Martínez-Luaña, Alba Gude-Santos, Manuel Fernández-Veiga +1 more
Distributed machine learning enables collaborative model training without centralizing data, but it also exposes learning processes to privacy...
DefenseMEDIUM
Behind the Refusal: Determining Guardrail Activation via Behavioral Monitoring
William Hackett, Peter Garraghan
As Large Language Models (LLMs) and agentic systems become integrated into real-world applications, ensuring their safety and security is critical....
DefenseMEDIUM
HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety
Navaneeth Sangameswaran, Preetham S, Ashmiya Lenin
We present HaloGuard 1.0, an open-weights implementation of the constitutional-classifier paradigm for input safety. It achieves state-of-the-art...
AttackMEDIUM
Black-Box Inference of LLM Architectural Properties with Restrictive API Access
Christopher Ellis, Shreyas Chaudhari, Mei-Yu Wang +3 more
In practice, most commercial LLM providers do not publicly release details of underlying LLM architectures. However, prior work has shown that given...
SurveyMEDIUM
Generative AI and Federated Learning for Intrusion Detection Systems: A Survey
Jiefei Liu, Abu Saleh Md Tayeen, Pratyay Kumar +5 more
Intrusion Detection Systems (IDSs) are essential for monitoring network traffic and identifying malicious activities in modern cyber-physical,...
BenchmarkMEDIUM
Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity
Brett Reynolds
Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model has followed an...
DefenseMEDIUM
HARC: Coupling Harmfulness and Refusal Directions for Robust Safety Alignment
Shei Pern Chua, Fangzhao Wu
Understanding how aligned LLMs internally represent safety is critical for diagnosing alignment vulnerabilities, as it explains why jailbreaks...
DefenseMEDIUM
Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks
MD Azizul Hakim, Md Shihab Uddin, Talha Ibne Anis
Lightweight machine learning models are increasingly proposed for intrusion detection in Industrial Internet of Things (IIoT) networks due to their...
BenchmarkMEDIUM
Minos: A Multi-Agent Collaborative Framework for Provenance-Based Backward Tracking
Jiahui Wang, Zhenyuan Li, Zhengkai Wang +2 more
Sophisticated cyber attacks, particularly Advanced Persistent Threats (APTs), require effective post-intrusion forensic analysis. Provenance-based...
AttackMEDIUM
Semantic Leakage and Privacy Preservation in Relay-Assisted Semantic Communications
Yalin E. Sagduyu, Tugba Erpek, Aylin Yener +1 more
Semantic communication (SemCom) has emerged as a promising paradigm in which the transmission of task-relevant information is prioritized over raw...
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