AI Threat Alert
Attack MEDIUM
LLM Reinforcement in Context
Thomas Rivasseau
Current Large Language Model alignment research mostly focuses on improving model robustness against adversarial attacks and misbehavior by training...
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 681–700 of 986 papers
Clear filters Tool MEDIUM
Scalable Hierarchical AI-Blockchain Framework for Real-Time Anomaly Detection in Large-Scale Autonomous Vehicle Networks
Rathin Chandra Shit, Sharmila Subudhi
The security of autonomous vehicle networks is facing major challenges, owing to the complexity of sensor integration, real-time performance demands,...
Defense MEDIUM
SGuard-v1: Safety Guardrail for Large Language Models
JoonHo Lee, HyeonMin Cho, Jaewoong Yun +3 more
We present SGuard-v1, a lightweight safety guardrail for Large Language Models (LLMs), which comprises two specialized models to detect harmful...
Attack MEDIUM
ToxSearch: Evolving Prompts for Toxicity Search in Large Language Models
Onkar Shelar, Travis Desell
Large Language Models remain vulnerable to adversarial prompts that elicit toxic content even after safety alignment. We present ToxSearch, a...
Attack MEDIUM
The 'Sure' Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models
Yuting Tan, Yi Huang, Zhuo Li
Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit...
Defense MEDIUM
Rethinking Deep Alignment Through The Lens Of Incomplete Learning
Thong Bach, Dung Nguyen, Thao Minh Le +1 more
Large language models exhibit systematic vulnerabilities to adversarial attacks despite extensive safety alignment. We provide a mechanistic analysis...
Attack MEDIUM
Explainable Transformer-Based Email Phishing Classification with Adversarial Robustness
Sajad U P
Phishing and related cyber threats are becoming more varied and technologically advanced. Among these, email-based phishing remains the most dominant...
Attack MEDIUM
ExplainableGuard: Interpretable Adversarial Defense for Large Language Models Using Chain-of-Thought Reasoning
Shaowei Guan, Yu Zhai, Zhengyu Zhang +2 more
Large Language Models (LLMs) are increasingly vulnerable to adversarial attacks that can subtly manipulate their outputs. While various defense...
Benchmark MEDIUM
BackWeak: Backdooring Knowledge Distillation Simply with Weak Triggers and Fine-tuning
Shanmin Wang, Dongdong Zhao
Knowledge Distillation (KD) is essential for compressing large models, yet relying on pre-trained "teacher" models downloaded from third-party...
Attack MEDIUM
On the Trade-Off Between Transparency and Security in Adversarial Machine Learning
Lucas Fenaux, Christopher Srinivasa, Florian Kerschbaum
Transparency and security are both central to Responsible AI, but they may conflict in adversarial settings. We investigate the strategic effect of...
Benchmark MEDIUM
SEAL: Subspace-Anchored Watermarks for LLM Ownership
Yanbo Dai, Zongjie Li, Zhenlan Ji +1 more
Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, demonstrating human-level...
Defense MEDIUM
EcoAlign: An Economically Rational Framework for Efficient LVLM Alignment
Ruoxi Cheng, Haoxuan Ma, Teng Ma +1 more
Large Vision-Language Models (LVLMs) exhibit powerful reasoning capabilities but suffer sophisticated jailbreak vulnerabilities. Fundamentally,...
Attack MEDIUM
Data Poisoning Vulnerabilities Across Healthcare AI Architectures: A Security Threat Analysis
Farhad Abtahi, Fernando Seoane, Iván Pau +1 more
Healthcare AI systems face major vulnerabilities to data poisoning that current defenses and regulations cannot adequately address. We analyzed eight...
Benchmark MEDIUM
PATCHEVAL: A New Benchmark for Evaluating LLMs on Patching Real-World Vulnerabilities
Zichao Wei, Jun Zeng, Ming Wen +8 more
Software vulnerabilities are increasing at an alarming rate. However, manual patching is both time-consuming and resource-intensive, while existing...
Benchmark MEDIUM
Robustness of LLM-enabled vehicle trajectory prediction under data security threats
Feilong Wang, Fuqiang Liu
The integration of large language models (LLMs) into automated driving systems has opened new possibilities for reasoning and decision-making by...
Benchmark MEDIUM
Synthetic Voices, Real Threats: Evaluating Large Text-to-Speech Models in Generating Harmful Audio
Guangke Chen, Yuhui Wang, Shouling Ji +2 more
Modern text-to-speech (TTS) systems, particularly those built on Large Audio-Language Models (LALMs), generate high-fidelity speech that faithfully...
Tool MEDIUM
ICX360: In-Context eXplainability 360 Toolkit
Dennis Wei, Ronny Luss, Xiaomeng Hu +6 more
Large Language Models (LLMs) have become ubiquitous in everyday life and are entering higher-stakes applications ranging from summarizing meeting...
Benchmark MEDIUM
Can AI Models be Jailbroken to Phish Elderly Victims? An End-to-End Evaluation
Fred Heiding, Simon Lermen
We present an end-to-end demonstration of how attackers can exploit AI safety failures to harm vulnerable populations: from jailbreaking LLMs to...
Defense MEDIUM
EnchTable: Unified Safety Alignment Transfer in Fine-tuned Large Language Models
Jialin Wu, Kecen Li, Zhicong Huang +3 more
Many machine learning models are fine-tuned from large language models (LLMs) to achieve high performance in specialized domains like code...
Benchmark MEDIUM
Taught by the Flawed: How Dataset Insecurity Breeds Vulnerable AI Code
Catherine Xia, Manar H. Alalfi
AI programming assistants have demonstrated a tendency to generate code containing basic security vulnerabilities. While developers are ultimately...
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