Attackers have begun creating fake ChatGPT workspaces dressed up as real companies. Then they invite employees through genuine OpenAI emails. The scheme is dangerous precisely because it does not look like ordinary phishing. The...
Artificial intelligence has now mastered the art of competing in “hacker tournaments,” surpassing nearly all human adversaries—executing its machinations with unprecedented celerity, profound cost-efficiency, and absolute tirelessness. The Israeli enterprise Tenzai proclaimed that its...
Fraudsters, propagandists, and state security apparatuses are increasingly co-opting language models—eschewing benign amusement in favor of extorting wealth and manipulating public discourse. In a newly published dossier, OpenAI fastidiously dissects dozens of such transgressions,...
An unidentified adversary manipulated the Claude chatbot, developed by Anthropic, to orchestrate a series of surgical strikes against Mexican governmental institutions, ultimately exfiltrating approximately 150 GB of sensitive data. Investigative findings suggest the breach...
Multi-turn Injection Planning System for LLM Evaluation MIPSEval is a modular framework for simulating and evaluating the behavior of Large Language Models (LLMs) in adversarial or structured multi-turn conversational scenarios. It supports both OpenAI-hosted...
Envision a scenario where your chatbot functions ostensibly as intended, preemptively suppressing a hazardous response, yet a data breach transpires subsequently in the most unanticipated of locales—the developer’s log viewer. Specialists from PromptArmor have...
OpenAI has released a security update for ChatGPT Atlas, a browser equipped with a built-in “agent mode” that can browse the web and act within it almost like a human—clicking, typing, and carrying out...
OpenAI has disclosed a security incident at the third-party web-analytics provider Mixpanel that affected a subset of users of the platform.openai.com API service. The event did not involve any breach of OpenAI’s own systems,...
A debate over security has erupted around Atlas, the new browser developed by OpenAI, after the German service Tuta—known for its fully end-to-end encrypted email and calendar—issued a warning to users about the risks...
A newly discovered vulnerability in ChatGPT Atlas, the experimental browser developed by OpenAI, allows attackers to silently inject malicious commands into the AI’s persistent memory, enabling the execution of arbitrary code on behalf of...
For the first time, the U.S. Department of Homeland Security has formally demanded that OpenAI disclose the identity of a ChatGPT user whose prompts appeared in a child pornography investigation. The warrant—issued to agents...
burpgpt burpgpt leverages the power of AI to detect security vulnerabilities that traditional scanners might miss. It sends web traffic to an OpenAI model specified by the user, enabling sophisticated analysis within the passive scanner. This...
