#model-extraction

[ follow ]
Artificial intelligence
fromComputerworld
1 day ago

Google fears massive attempt to clone Gemini AI through model extraction

Google detected and blocked over 100,000 prompts aimed at extracting Gemini's proprietary reasoning capabilities to prevent model extraction and intellectual property theft.
fromTechzine Global
1 day ago

OpenAI accuses DeepSeek of misusing AI models

According to the company behind ChatGPT, DeepSeek is systematically attempting to extract knowledge from leading American AI systems in order to improve its own models. In the memo, which OpenAI sent to the U.S. House Select Committee on Strategic Competition between the U.S. and the Chinese Communist Party, OpenAI outlines attempts to circumvent technical and access restrictions. The company claims that accounts linked to DeepSeek employees have developed methods to access AI models via external, obfuscated network routes.
Artificial intelligence
fromArs Technica
2 days ago

Attackers prompted Gemini over 100,000 times while trying to clone it, Google says

On Thursday, Google announced that "commercially motivated" actors have attempted to clone knowledge from its Gemini AI chatbot by simply prompting it. One adversarial session reportedly prompted the model more than 100,000 times across various non-English languages, collecting responses ostensibly to train a cheaper copycat. Google published the findings in what amounts to a quarterly self-assessment of threats to its own products that frames the company as the victim and the hero, which is not unusual in these self-authored assessments.
Artificial intelligence
Information security
fromwww.socialmediatoday.com
2 days ago

Google Says That Scam Tactics Are Evolving Through AI Usage

AI tools dramatically enhance attackers' productivity, enabling more convincing phishing, model-extraction corporate espionage, and nation-state use for technical research and targeted campaigns.
Artificial intelligence
fromMedium
3 months ago

From Red Teaming to Real Protection: Building Enterprise AI Security for the Agentic Era

Autonomous AI agents with memory, tool access, and multi-step abilities create novel, high-stakes security risks that traditional security tools cannot adequately address.
[ Load more ]