AI Threat AlertAttackMEDIUM
Kernel-Managed Shared Memory for System-Wide Personalization
Ryan Lum, Yongfeng Zhang
AI systems become more useful when they can adapt to the people using them, but in multi-agent systems, useful context learned by one agent often...
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 681–700 of 1,739 papers
Clear filtersAttackMEDIUM
Active Adaptation, Not Static Defense: Temporal Dynamics of Preventative Steering in Adversarial Fine-Tuning
Jing Guan, Yachao Yang, Zhaoliang Liu +3 more
Large language models remain fragile against malicious fine-tuning, motivating training-time defenses against harmful persona drift. Preventative...
DefenseMEDIUM
Understanding the Security Boundary of Obfuscation-based On-Device LLM Protection
Hanyi Zhou, Chenyang Li, Yuanzhe Pang +3 more
Trusted Execution Environments (TEEs) offer a promising mechanism for safeguarding the intellectual property of on-device Large Language Models...
AttackMEDIUM
Belief-State Engine: Augmenting LLMs for Principled Planning Under Partial Observability
Arnab Chattopadhayay, Debdipta Halder
Large language model agents produce fluent action sequences across a wide range of tasks, yet they fail in characteristic ways once the environment...
AttackMEDIUM
What Makes Adversarial Examples Transfer Across Deepfake Detectors?
Rafael M. Mamede, Pedro C. Neto, Ana F. Sequeira
Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and...
BenchmarkMEDIUM
CS-Guard: Benchmarking LLM Guardrails for Code Generation Security
Jinyang Li, Mingyu Guo, Hung X. Nguyen
Large language models (LLMs) have been ex- ploited to generate malware, but the effective- ness of guardrails for code generation secu- rity remains...
SurveyHIGH
Black-Box Red Teaming of Agentic AI: A Taxonomy-Driven Framework for Automated Risk Discovery
Divyanshu Kumar, Nitin Aravind Birur, Tanay Baswa +2 more
Agentic systems are rapidly moving to production, where they read untrusted inputs, call tools with real permissions, and act autonomously, expanding...
AttackHIGH
Robust Industrial Cyber Physical Classification Using Neuromorphic Temporal Embeddings and Hybrid SNN XGBoost Under Machine Unlearning Attacks
Ammar Kamoona, Sajad Koushkbaghi, Mahdi Jalili +2 more
The digitalisation of electrical distribution networks has increased the exposure of power-grid infrastructure to cyber attacks. Existing intrusion...
OtherLOW
The Vibe Shift in Software Engineering: Evaluating AI-Led Conversational Programming for Performance, Cognition, and Responsible Adoption
Sales G. Aribe, Louie Jay S. Labastida
This study evaluates Vibe Coding, an emerging AI-led conversational programming paradigm that enables developers to generate software through...
AttackHIGH
Arbitrary Cipher Attacks Against Large Language Models Do Not Require Fine-Tuning
Thomas Rivasseau
Large language model safety and security research is preoccupied with, among other things, detecting and preventing jailbreak attacks: alignment...
AttackHIGH
Concept drift mitigation through community and spectral graph analysis for the detectionof cyberattacks in network traffic
Julien Michel, Abdul Qadir Khan, Majed Jaber +1 more
In network traffic, legitimate behaviours and attack techniques evolve jointly - the phenomenon known as 'concept drift' [1]. Every detector is...
BenchmarkHIGH
An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks
Viet K. Nguyen, Mohammad I. Husain
Agentic AI frameworks let a language model plan, keep memory, and call tools that reach real files, mail, and services. Most of these agents also...
SurveyHIGH
LLMSec-AV: A Vulnerability Taxonomy and LLM-Driven Software Weakness Discovery Framework for Autonomous Vehicles
Md. Wasiul Haque, Sagar Dasgupta, Mizanur Rahman
Automated vehicles rely on millions of lines of safety-critical software, yet general-purpose analyzers do not understand which code can affect...
BenchmarkMEDIUM
PrivEscalate: Measuring and Augmenting the Threat of LLM-Automated Linux Privilege Escalation
Yixuan Liu, Zilong Zhen, Yin Wu +1 more
As Large Language Model (LLM) agents increasingly automate offensive operations across the cyber kill chain, their efficacy in complex local...
SurveyMEDIUM
Measuring the Security of the Evolving Software Supply Chain: a Research Agenda
Sarah Meriem Ourari
Software supply chain security has become increasingly critical due to the widespread reliance on third-party dependencies and the growing attack...
OtherLOW
Evidence-Grounded Retrieval for Investigation Hunt Lead Generation from CTI Reports
Akash Prakash, Boubakr Nour, Makan Pourzandi +2 more
Threat hunting increasingly depends on converting unstructured knowledge (e.g., Cyber Threat Intelligence reports) into actionable hunt leads:...
ToolMEDIUM
MemSentry: A Framework for Detecting Persistent Memory Poisoning in Agentic AI
Ayan Roy, Kaustuvi Basu
Agentic AI systems with persistent memory introduce a distinct attack surface known as memory poisoning, in which adversarially crafted content is...
DefenseLOW
Combating Instruction Conflict via Energy-Driven Latent Conflict Detection
Mingyu Ma, Yuxin Wu, Jingbo Wang +3 more
Large Language Models (LLMs) are increasingly deployed with hierarchical instructions, yet they remain vulnerable to conflicts in which user...
AttackMEDIUM
In RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning
Iliano Fasolino
Retrieval-augmented generation (RAG) grounds a language model in retrieved documents, which reduces hallucination but creates a new attack surface:...
AttackMEDIUM
Compositional Multilingual and Behavioral Attribute Steering
Hyun Gu Kang, Daniil Gurgurov, Tanja Baeumel +2 more
This study examines the compositionality of steering vectors for language and behavioral control in large language models. Focusing on language,...
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