AI Threat AlertDefenseMEDIUM
Intent-Aware Protection for AI Agents
Fady Copty, Neta Haiby, Max Braitmaiere +1 more
AI agents increasingly access enterprise data, invoke powerful tools, and act with limited human oversight. Existing security defenses primarily...
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 1–20 of 404 papers
Clear filtersDefenseMEDIUM
Agreement Is Not Assurance: Evidence-Independent Safety Gates for Agentic AI in DER-Rich Distribution Grids
Qianxue Xia
Physics-based safety gates for large language model (LLM) agents can approve unsafe actions when the agent and gate rely on the same corrupted...
DefenseMEDIUM
When Coding Agents Get Arms: Safety Risks Across the Digital-Physical Boundary
Yiming Sun, Mi Zhang
Advances in spatial understanding have enabled frontier models to power coding agents that control a real robot arm zero-shot and end-to-end, without...
DefenseMEDIUM
ErosionBench: Probing Alignment Decay in Enterprise Multi-Agent Systems
Riya Bharathwaj, Akshara Prabhakar, Roshan Ram +4 more
As enterprises delegate consequential work to multi-agent LLM systems, benign-looking requests can escalate into unsafe actions as they propagate...
DefenseMEDIUM
Stress Testing Chain-of-Thought Monitoring Against Covert Misalignment
Yao Huang, Yifan Wang, Yitong Sun +2 more
As LLM agents advance rapidly in autonomy, the risk of hidden objectives that bypass safety constraints becomes increasingly plausible....
DefenseMEDIUM
Addition by Subtraction: Toward Mitigating Fragile Safety Alignment in Large Language Models
Hamid Dashtbani, Alexandra Dmitrienko
Large language models (LLMs) undergo safety alignment to prevent harmful generations, yet they remain vulnerable to jailbreak attacks. Recent work...
DefenseMEDIUM
SafeStart: Mitigating the Overlooked Safety Cost of Active Expert Reduction in MoE LLM Serving
Erfan Baghaei Potraghloo, Saeid Shokoufa, Seyedarmin Azizi +4 more
Mixture-of-Experts (MoE) language models send each token through a few of many expert subnetworks. Serving methods make these models faster by...
DefenseMEDIUM
TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport
Chuancheng Shi, Shangze Li, Wenhua Wu +5 more
Despite their remarkable capabilities, large foundation models (LFMs) remain susceptible to adversarial manipulation. Current safety intervention...
DefenseMEDIUM
TraceRouter++: Causal Semantic Routing Realignment via Optimal Transport
Chuancheng Shi, Shangze Li, Wenhua Wu +5 more
Despite their remarkable capabilities, large foundation models (LFMs) remain susceptible to adversarial manipulation. Current safety intervention...
DefenseMEDIUM
Voluntary Servitude: Weaponized Safety Warning Mechanisms for Controlling AI Agents
Ilan Zendel, Matan Levy, Stav Cohen +2 more
LLM agents increasingly act on information retrieved from public sources they treat as credible, which turns a manipulated recommendation into a...
DefenseMEDIUM
PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models
Junyu Lin, Mengjie Wu, Yonghao Dong +11 more
As streaming generation becomes the dominant serving paradigm for both text-only and multimodal large language models, ensuring safety throughout the...
DefenseMEDIUM
PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models
Junyu Lin, Mengjie Wu, Yonghao Dong +11 more
As streaming generation becomes the dominant serving paradigm for both text-only and multimodal large language models, ensuring safety throughout the...
DefenseMEDIUM
StateFence: Task-State Protection Against Evidence-Chain Contamination in Blue-Team LLM Agents
Haowen Dai, Alejandro Guerra-Manzanares
Indirect prompt injection creates a distinctive risk for blue-team Large Language Model (LLM) agents in Security Operations Centers (SOCs). Malicious...
DefenseMEDIUM
The Envelope Layer: An Underestimated Surface of LLM Agent Defense
Yuelin Han
Prior work framed the envelope layer as the channel through which malicious content enters an agent, and established it as a defense surface...
DefenseMEDIUM
ARISE: Authentic Reference-Informed Stability Enhancement for Continual Multimodal Forgery Detection
Yuchen Zhang, Yaxiong Wang, Yujiao Wu +6 more
Multimodal forgery detection is commonly studied under a static assumption: training attacks are expected to approximate those encountered after...
DefenseMEDIUM
Steering for Safety, Hijacking for Profit: Trojan Threats in the LLM Activation Steering Supply Chain
Yu Yan, Jiahao Chen, Siqi Lu +4 more
As large language models (LLMs) are increasingly integrated into Web search, online recommendation, and intelligent decision-making, the third-party...
DefenseMEDIUM
ClawMMU: Protection-Coherent Virtual Memory for Stateful LLM Agents
Jinhao Hu, Bardia Mohammadi, Mofasshara Binte Rafique +4 more
AI agents keep long-term memory, much of which comes from web pages and tool results. Agent harnesses, the software that runs the model, do not...
DefenseMEDIUM
SpanGuard: Decoupling Instruction Localization from Authorization for Lightweight IPI Defense
Yinxiang Wang, Zehua Ma, Kejiang Chen +2 more
LLM-based guardrails are effective against indirect prompt injection (IPI), but their performance depends heavily on model capability: as the...
DefenseMEDIUM
PRISM: Transfer and Limits of Activation Interventions in Tool-Calling Language Models
Giovana Kerche Bonás, Thales Sales Almeida, Marcelo da Silva Reis +2 more
Recent literature shows that unsafe tool calls can often accompany textual refusals in language models. To investigate this hidden vulnerability, we...
DefenseMEDIUM
Counterfactual Neighborhood Risk Fields: Evidence-Grounded Selective Safety for Vision-Language Models
Tianshi Wang, Jingsong Wang, Fengling Li +3 more
Representation-based safety defenses for vision-language models (VLMs) often learn to separate harmful from benign inputs, but separation alone does...
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