Artificial Intelligence
New "Echo Chamber" attack bypasses advanced LLM safeguards by subtly manipulating conversational context, proving highly effective across leading AI models.
Hi, what are you looking for?
SecurityWeek
All posts tagged "AI jailbreak"
Artificial Intelligence
A new attack technique named Policy Puppetry can break the protections of major gen-AI models to produce harmful outputs.
Artificial Intelligence
Cato Networks discovers a new LLM jailbreak technique that relies on creating a fictional world to bypass a model’s security controls.
Artificial Intelligence
Two Microsoft researchers have devised a new jailbreak method that bypasses the safety mechanisms of most AI systems.
Artificial Intelligence
DeepSeek’s susceptibility to jailbreaks has been compared by Cisco to other popular AI models, including from Meta, OpenAI and Google.
Artificial Intelligence
Researchers found a jailbreak method that exposed DeepSeek’s system prompt, while others have analyzed the DDoS attacks aimed at the new gen-AI.
Artificial Intelligence
Different research teams have demonstrated jailbreaks against ChatGPT, DeepSeek, and Alibaba’s Qwen AI models.
Artificial Intelligence
China’s DeepSeek blamed sign-up disruptions on a cyberattack as researchers started finding vulnerabilities in the R1 AI model.
Artificial Intelligence
New jailbreak technique tricked ChatGPT into generating Python exploits and a malicious SQL injection tool.
Artificial Intelligence
Deceptive Delight is a new AI jailbreak that has been successfully tested against eight models with an average success rate of 65%.
Artificial Intelligence
Microsoft has tricked several gen-AI models into providing forbidden information using a jailbreak technique named Skeleton Key.
Cybercrime
Noteworthy stories that might have slipped under the radar: China blames NSA for a cyberattack, AI jailbreaks, and Netography spin-off.
IoT Security
PCA Cyber Security has discovered critical vulnerabilities in the BlueSDK Bluetooth stack that could have allowed remote code execution on car systems.
Artificial Intelligence
Network Security
Mobile & Wireless
Details have been disclosed for an eSIM hacking method that could impact many, but the industry is taking action.
Data Breaches
Cybersecurity Funding
Artificial Intelligence