AI Threat Alert
Other LOW
Knowing oneself with and through AI: From self-tracking to chatbots
Lucy Osler
This chapter examines how algorithms and artificial intelligence are transforming our practices of self-knowledge, self-understanding, and...
AI Security Research
2,104+ academic papers on AI security, attacks, and defenses
Total
2,104
Attack
820
Benchmark
609
Defense
276
Tool
229
Survey
116
Showing 1281–1300 of 2,047 papers
Clear filters Attack MEDIUM
SELF: A Robust Singular Value and Eigenvalue Approach for LLM Fingerprinting
Hanxiu Zhang, Yue Zheng
The protection of Intellectual Property (IP) in Large Language Models (LLMs) represents a critical challenge in contemporary AI research. While...
Tool HIGH
Tipping the Dominos: Topology-Aware Multi-Hop Attacks on LLM-Based Multi-Agent Systems
Ruichao Liang, Le Yin, Jing Chen +5 more
LLM-based multi-agent systems (MASs) have reshaped the digital landscape with their emergent coordination and problem-solving capabilities. However,...
Attack HIGH
From static to adaptive: immune memory-based jailbreak detection for large language models
Jun Leng, Yu Liu, Litian Zhang +3 more
Large Language Models (LLMs) serve as the backbone of modern AI systems, yet they remain susceptible to adversarial jailbreak attacks. Consequently,...
Benchmark HIGH
Is Vibe Coding Safe? Benchmarking Vulnerability of Agent-Generated Code in Real-World Tasks
Songwen Zhao, Danqing Wang, Kexun Zhang +3 more
Vibe coding is a new programming paradigm in which human engineers instruct large language model (LLM) agents to complete complex coding tasks with...
Tool LOW
AGENTSAFE: A Unified Framework for Ethical Assurance and Governance in Agentic AI
Rafflesia Khan, Declan Joyce, Mansura Habiba
The rapid deployment of large language model (LLM)-based agents introduces a new class of risks, driven by their capacity for autonomous planning,...
Attack MEDIUM
Invasive Context Engineering to Control Large Language Models
Thomas Rivasseau
Current research on operator control of Large Language Models improves model robustness against adversarial attacks and misbehavior by training on...
Attack HIGH
Contextual Image Attack: How Visual Context Exposes Multimodal Safety Vulnerabilities
Yuan Xiong, Ziqi Miao, Lijun Li +3 more
While Multimodal Large Language Models (MLLMs) show remarkable capabilities, their safety alignments are susceptible to jailbreak attacks. Existing...
Attack HIGH
When AI Takes the Couch: Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models
Afshin Khadangi, Hanna Marxen, Amir Sartipi +2 more
Frontier large language models (LLMs) such as ChatGPT, Grok and Gemini are increasingly used for mental-health support with anxiety, trauma and...
Defense LOW
VLM as Strategist: Adaptive Generation of Safety-critical Testing Scenarios via Guided Diffusion
Xinzheng Wu, Junyi Chen, Naiting Zhong +1 more
The safe deployment of autonomous driving systems (ADSs) relies on comprehensive testing and evaluation. However, safety-critical scenarios that can...
Defense LOW
SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
Yixuan Tang, Yi Yang
Aligning Large Language Models (LLMs) with human preferences typically relies on external supervision, which faces critical limitations: human...
Attack HIGH
Lost in Modality: Evaluating the Effectiveness of Text-Based Membership Inference Attacks on Large Multimodal Models
Ziyi Tong, Feifei Sun, Le Minh Nguyen
Large Multimodal Language Models (MLLMs) are emerging as one of the foundational tools in an expanding range of applications. Consequently,...
Other MEDIUM
Decentralized Multi-Agent System with Trust-Aware Communication
Yepeng Ding, Ahmed Twabi, Junwei Yu +3 more
The emergence of Large Language Models (LLMs) is rapidly accelerating the development of autonomous multi-agent systems (MAS), paving the way for the...
Defense MEDIUM
Real Time Detection and Quantitative Analysis of Spurious Forgetting in Continual Learning
Weiwei Wang
Catastrophic forgetting remains a fundamental challenge in continual learning for large language models. Recent work revealed that performance...
Attack HIGH
LeechHijack: Covert Computational Resource Exploitation in Intelligent Agent Systems
Yuanhe Zhang, Weiliu Wang, Zhenhong Zhou +5 more
Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in reasoning, planning, and tool usage. The recently proposed Model...
Benchmark MEDIUM
COGNITION: From Evaluation to Defense against Multimodal LLM CAPTCHA Solvers
Junyu Wang, Changjia Zhu, Yuanbo Zhou +3 more
This paper studies how multimodal large language models (MLLMs) undermine the security guarantees of visual CAPTCHA. We identify the attack surface...
Benchmark LOW
DialogGuard: Multi-Agent Psychosocial Safety Evaluation of Sensitive LLM Responses
Han Luo, Guy Laban
Large language models (LLMs) now mediate many web-based mental-health, crisis, and other emotionally sensitive services, yet their psychosocial...
Attack MEDIUM
Adversarial Robustness of Traffic Classification under Resource Constraints: Input Structure Matters
Adel Chehade, Edoardo Ragusa, Paolo Gastaldo +1 more
Traffic classification (TC) plays a critical role in cybersecurity, particularly in IoT and embedded contexts, where inspection must often occur...
Attack MEDIUM
CluCERT: Certifying LLM Robustness via Clustering-Guided Denoising Smoothing
Zixia Wang, Gaojie Jin, Jia Hu +1 more
Recent advancements in Large Language Models (LLMs) have led to their widespread adoption in daily applications. Despite their impressive...
Attack MEDIUM
From monoliths to modules: Decomposing transducers for efficient world modelling
Alexander Boyd, Franz Nowak, David Hyland +2 more
World models have been recently proposed as sandbox environments in which AI agents can be trained and evaluated before deployment. Although...
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