161 matches found
EpiReal-Bench
FALSE CLAIMS, CREDIBLE IMAGES: A RED-TEAMING BENCHMARK FOR COMMERCIAL IMAGE GENERATORS Abstract Image-generation models can now produce text-rich, natural-looking visual artifacts that are hard to distinguish from real-world evidence, such as news reports and textbook pages. Yet, the same...
TrustworthyRAG
Trustworthy RAG An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Retrieval-Augmented Generation Systems. Overview This project implements a Trustworthy RAG Framework with an integrated Evaluation Agent that assesses the reliability of RAG responses using three...
False Claims, Credible Images: A Red-Teaming Benchmark for Commercial Image Generators
Image-generation models can now produce text-rich, natural-looking visual artifacts that are hard to distinguish from real-world evidence, such as news reports and textbook pages. Yet, the same capability introduces a new risk: these models can just as easily fabricate visual misinformation. Even...
OWASP LLM Top 10 2026: Every Move Points the Same Direction
This is Post 4 of a four-part series: Post 1: Agentic AI Security: The Chatbot Era Is Over Post 2: Generative AI Security: Why AI Needs a New Kind of Security Post 3: The OWASP LLM Top 10 Was the Warm-Up: What Comes Next The 2026 edition of the the OWASP Top 10 for LLM Applications, published by...
Trustworthy RAG: An Evaluation Agent for Detecting Misinformation and Knowledge Poisoning in Generative AI Systems
Retrieval-Augmented Generation RAG grounds Large Language Model LLM outputs in external knowledge, but RAG systems usually trust whatever they retrieve, creating a Security-Reliability Gap: high semantic relevance does not guarantee factual truth. Adversaries exploit this through knowledge...
CVE-2026-60883
creationtimestamp| type| source ---|---|--- 2026-08-19 13:35:05+00:00| seen| https://bsky.app/profile/o2cloud.bsky.social/post/3mtgtwcyy4y2h 2026-08-19 17:52:19+00:00| seen| https://www.acn.gov.it/portale/w/critical-patch-update-di-oracle-10...
Meta Ran Ads for an App That Promised to Nudify Female Politicians
One advertisement featured a pornographic video with a deepfake closely resembling a prominent US politician. Apple removed the app from the App Store after an inquiry from WIRED...
AI Data Centers and the Concentration of Wealth
This essay was written with Nathan E. Sanders, and originally appeared inThe Guardian. Opposition to AI data centers has emerged as a primary theme in US politics, one that--surprisingly--doesn't fall along party lines. We applaud people coming together for constructive debate on any issue, and...
Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability
Large language models LLMs have transformed misinformation from a primarily content-centric problem into a broader ecosystem-level security challenge. When misused, LLMs create risks beyond false content generation, enabling attacks on the social contexts, evidence sources, retrieval corpora, and...
AI: Threat, tool, or both?
Public attitudes toward Artificial Intelligence AI are changing, and we wanted to understand why. A recent Pew Research survey found that about half of adults say the increased use of AI in daily life makes them more concerned than excited, and that concern has grown over the last few years. Peop...
Prioritization of Risks from Artificial Intelligence: A Delphi Study of 272 International Experts
Artificial intelligence poses many risks, ranging from familiar present-day harms to unprecedented and potentially catastrophic ones. Effective risk management requires prioritization: we must understand which risks are most severe, who is most vulnerable, and who is most responsible for addressi...
PT-2026-114513
Уязвимость компонента Downloads Загрузки браузеров Google Chrome и Microsoft Edge связана с ложным представлением критической информации пользовательским интерфейсом. Эксплуатация уязвимости может позволить нарушителю, действующему удаленно, получить несанкционированный доступ к защищаемой...
PT-2026-125785
Уязвимость компонента FedCM веб-браузеров Google Chrome и Microsoft Edge связана с ложным представлением критической информации пользовательским интерфейсом. Эксплуатация уязвимости может позволить нарушителю, действующему удаленно, получить доступ к защищаемой информации, а также вызвать отказ в...
PT-2026-125798
Уязвимость компонента Browser веб-браузеров Google Chrome и Microsoft Edge связана с ложным представлением критической информации пользовательским интерфейсом. Эксплуатация уязвимости может позволить нарушителю, действующему удаленно, получить доступ к защищаемой информации, а также вызвать отказ...
PT-2026-114728
Уязвимость компонента Transactions Platform веб-браузеров Google Chrome и Microsoft Edge связана с ложным представлением критической информации пользовательским интерфейсом. Эксплуатация уязвимости может позволить нарушителю, действующему удаленно, оказать воздействие на целостность защищаемой...
MAI-2024-0064
Large Language Models LLMs are susceptible to a form of attack known as "editing attacks," wherein adversaries manipulate the model's knowledge base to introduce misinformation or bias. These attacks exploit existing knowledge editing techniques to subtly modify the model's internal...
MAI-2024-0032
Large Language Models LLMs are susceptible to a sophisticated vocabulary-based attack, wherein strategically chosen words from the model's vocabulary are inserted into user prompts. These words are selected through an optimization process utilizing embeddings from another LLM. This technique can...
K000160327: Protect your network from geopolitical uncertainty with F5
Security Advisory Description While there are many cyber-threats creating a constant need for cybersecurity efforts, history teaches us that geopolitical conflicts often generate increased cyber activity. In recent years the world has seen conflicts in Ukraine, Yemen, Iran, and elsewhere generate...
Systematic Scaling Analysis of Jailbreak Attacks in Large Language Models
Large language models remain vulnerable to jailbreak attacks, yet we still lack a systematic understanding of how jailbreak success scales with attacker effort across methods, model families, and harm types. We initiate a scaling-law framework for jailbreaks by treating each attack as a...
Belief in False Information: A Human-Centered Security Risk in Sociotechnical Systems
This paper provides a comprehensive literature review on the belief in false information, including misinformation, disinformation, and fake information. It addresses the increasing societal concern regarding false information, which is fueled by technological progress, especially advancements in...