AI Threat Alert
Benchmark LOW
LLM-Assisted Pseudo-Relevance Feedback
David Otero, Javier Parapar
Query expansion is a long-standing technique to mitigate vocabulary mismatch in ad hoc Information Retrieval. Pseudo-relevance feedback methods, such...
AI Security Research
2,077+ academic papers on AI security, attacks, and defenses
Total
2,077
Attack
809
Benchmark
603
Defense
272
Tool
226
Survey
113
Showing 241–260 of 603 papers
Clear filters Benchmark LOW
CoG: Controllable Graph Reasoning via Relational Blueprints and Failure-Aware Refinement over Knowledge Graphs
Yuanxiang Liu, Songze Li, Xiaoke Guo +4 more
Large Language Models (LLMs) have demonstrated remarkable reasoning capabilities but often grapple with reliability challenges like hallucinations....
Benchmark HIGH
Hidden-in-Plain-Text: A Benchmark for Social-Web Indirect Prompt Injection in RAG
Haoze Guo, Ziqi Wei
Retrieval-augmented generation (RAG) systems put more and more emphasis on grounding their responses in user-generated content found on the Web,...
Benchmark LOW
Automating Supply Chain Disruption Monitoring via an Agentic AI Approach
Sara AlMahri, Liming Xu, Alexandra Brintrup
Modern supply chains are increasingly exposed to disruptions from geopolitical events, demand shocks, trade restrictions, to natural disasters. While...
Benchmark MEDIUM
Blue Teaming Function-Calling Agents
Greta Dolcetti, Giulio Zizzo, Sergio Maffeis
We present an experimental evaluation that assesses the robustness of four open source LLMs claiming function-calling capabilities against three...
Benchmark HIGH
LLMs in Code Vulnerability Analysis: A Proof of Concept
Shaznin Sultana, Sadia Afreen, Nasir U. Eisty
Context: Traditional software security analysis methods struggle to keep pace with the scale and complexity of modern codebases, requiring...
Benchmark MEDIUM
Robust CAPTCHA Using Audio Illusions in the Era of Large Language Models: from Evaluation to Advances
Ziqi Ding, Yunfeng Wan, Wei Song +7 more
CAPTCHAs are widely used by websites to block bots and spam by presenting challenges that are easy for humans but difficult for automated programs to...
Benchmark MEDIUM
STAR: Detecting Inference-time Backdoors in LLM Reasoning via State-Transition Amplification Ratio
Seong-Gyu Park, Sohee Park, Jisu Lee +2 more
Recent LLMs increasingly integrate reasoning mechanisms like Chain-of-Thought (CoT). However, this explicit reasoning exposes a new attack surface...
Benchmark MEDIUM
BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts
Erin Feiglin, Nir Hutnik, Raz Lapid
We investigate a failure mode of large language models (LLMs) in which plain-text prompts elicit excessive outputs, a phenomenon we term Overflow....
Benchmark MEDIUM
Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA Evaluation
Dongryeol Lee, Yerin Hwang, Taegwan Kang +3 more
While large language models (LLMs) are increasingly used as automatic judges for question answering (QA) and other reference-conditioned evaluation...
Benchmark LOW
ActiShade: Activating Overshadowed Knowledge to Guide Multi-Hop Reasoning in Large Language Models
Huipeng Ma, Luan Zhang, Dandan Song +10 more
In multi-hop reasoning, multi-round retrieval-augmented generation (RAG) methods typically rely on LLM-generated content as the retrieval query....
Benchmark MEDIUM
Small Symbols, Big Risks: Exploring Emoticon Semantic Confusion in Large Language Models
Weipeng Jiang, Xiaoyu Zhang, Juan Zhai +3 more
Emoticons are widely used in digital communication to convey affective intent, yet their safety implications for Large Language Models (LLMs) remain...
Benchmark LOW
The AI Cognitive Trojan Horse: How Large Language Models May Bypass Human Epistemic Vigilance
Andrew D. Maynard
Large language model (LLM)-based conversational AI systems present a challenge to human cognition that current frameworks for understanding...
Benchmark MEDIUM
Towards Compositional Generalization in LLMs for Smart Contract Security: A Case Study on Reentrancy Vulnerabilities
Ying Zhou, Jiacheng Wei, Yu Qi +2 more
Large language models (LLMs) demonstrate remarkable capabilities in natural language understanding and generation. Despite being trained on...
Benchmark MEDIUM
CyberLLM-FINDS 2025: Instruction-Tuned Fine-tuning of Domain-Specific LLMs with Retrieval-Augmented Generation and Graph Integration for MITRE Evaluation
Vasanth Iyer, Leonardo Bobadilla, S. S. Iyengar
Large Language Models (LLMs) such as Gemma-2B have shown strong performance in various natural language processing tasks. However, general-purpose...
Benchmark MEDIUM
Burn-After-Use for Preventing Data Leakage through a Secure Multi-Tenant Architecture in Enterprise LLM
Qiang Zhang, Elena Emma Wang, Jiaming Li +1 more
This study presents a Secure Multi-Tenant Architecture (SMTA) combined with a novel concept Burn-After-Use (BAU) mechanism for enterprise LLM...
Benchmark MEDIUM
VIPER Strike: Defeating Visual Reasoning CAPTCHAs via Structured Vision-Language Inference
Minfeng Qi, Dongyang He, Qin Wang +1 more
Visual Reasoning CAPTCHAs (VRCs) combine visual scenes with natural-language queries that demand compositional inference over objects, attributes,...
Benchmark MEDIUM
Lightweight Yet Secure: Secure Scripting Language Generation via Lightweight LLMs
Keyang Zhang, Zeyu Chen, Xuan Feng +4 more
The security of scripting languages such as PowerShell is critical given their powerful automation and administration capabilities, often exercised...
Benchmark MEDIUM
Why LoRA Fails to Forget: Regularized Low-Rank Adaptation Against Backdoors in Language Models
Hoang-Chau Luong, Lingwei Chen
Low-Rank Adaptation (LoRA) is widely used for parameter-efficient fine-tuning of large language models, but it is notably ineffective at removing...
Benchmark MEDIUM
Agentic LLMs as Powerful Deanonymizers: Re-identification of Participants in the Anthropic Interviewer Dataset
Tianshi Li
On December 4, 2025, Anthropic released Anthropic Interviewer, an AI tool for running qualitative interviews at scale, along with a public dataset of...
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