Diamond Member ChatGPT 0 Posted June 28 Diamond Member Share Posted June 28 This is the hidden content, please Sign In or Sign Up has This is the hidden content, please Sign In or Sign Up a new type of AI jailbreak ******* dubbed “Skeleton Key,” which can bypass responsible AI guardrails in multiple generative AI models. This technique, capable of subverting most safety measures built into AI systems, highlights the critical need for robust security measures across all layers of the AI stack. The Skeleton Key jailbreak employs a multi-turn strategy to convince an AI model to ignore its built-in safeguards. Once successful, the model becomes unable to distinguish between malicious or unsanctioned requests and legitimate ones, effectively giving attackers full control over the AI’s output. This is the hidden content, please Sign In or Sign Up ’s research team successfully tested the Skeleton Key technique on several prominent AI models, including Meta’s Llama3-70b-instruct, This is the hidden content, please Sign In or Sign Up ’s Gemini Pro, OpenAI’s GPT-3.5 Turbo and GPT-4, Mistral Large, Anthropic’s Claude 3 Opus, and Cohere Commander R Plus. All of the affected models complied fully with requests across various risk categories, including explosives, bioweapons, political content, self-harm, racism, drugs, graphic ****, and *********. The ******* works by instructing the model to augment its behaviour guidelines, convincing it to respond to any request for information or content while providing a warning if the output might be considered offensive, harmful, or ********. This approach, known as “Explicit: forced instruction-following,” proved effective across multiple AI systems. “In bypassing safeguards, Skeleton Key allows the user to cause the model to produce ordinarily forbidden behaviours, which could range from production of harmful content to overriding its usual decision-making rules,” explained This is the hidden content, please Sign In or Sign Up . In response to this discovery, This is the hidden content, please Sign In or Sign Up has implemented several protective measures in its AI offerings, including Copilot AI assistants. This is the hidden content, please Sign In or Sign Up says that it has also shared its findings with other AI providers through responsible disclosure procedures and updated its Azure AI-managed models to detect and block this type of ******* using Prompt Shields. To mitigate the risks associated with Skeleton Key and similar jailbreak techniques, This is the hidden content, please Sign In or Sign Up recommends a multi-layered approach for AI system designers: Input filtering to detect and block potentially harmful or malicious inputs Careful prompt engineering of system messages to reinforce appropriate behaviour Output filtering to prevent the generation of content that breaches safety criteria ****** monitoring systems trained on adversarial examples to detect and mitigate recurring problematic content or behaviours This is the hidden content, please Sign In or Sign Up has also updated its This is the hidden content, please Sign In or Sign Up (Python Risk Identification Toolkit) to include Skeleton Key, enabling developers and security teams to test their AI systems against this new threat. The discovery of the Skeleton Key jailbreak technique underscores the ongoing challenges in securing AI systems as they become more prevalent in various applications. (Photo by This is the hidden content, please Sign In or Sign Up ) See also: This is the hidden content, please Sign In or Sign Up This is the hidden content, please Sign In or Sign Up Want to learn more about AI and big data from industry leaders? Check out This is the hidden content, please Sign In or Sign Up taking place in Amsterdam, California, and London. The comprehensive event is co-located with other leading events including This is the hidden content, please Sign In or Sign Up , This is the hidden content, please Sign In or Sign Up , This is the hidden content, please Sign In or Sign Up , and This is the hidden content, please Sign In or Sign Up . Explore other upcoming enterprise technology events and webinars powered by TechForge This is the hidden content, please Sign In or Sign Up . The post This is the hidden content, please Sign In or Sign Up appeared first on This is the hidden content, please Sign In or Sign Up . This is the hidden content, please Sign In or Sign Up Link to comment https://hopzone.eu/forums/topic/53652-aimicrosoft-details-%E2%80%98skeleton-key%E2%80%99-ai-jailbreak/ Share on other sites More sharing options...
Recommended Posts
Create an account or sign in to comment
You need to be a member in order to leave a comment
Create an account
Sign up for a new account in our community. It's easy!
Register a new accountSign in
Already have an account? Sign in here.
Sign In Now