3 matches found
AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
As LLMs are increasingly deployed in real-world applications, ensuring their ability to refuse malicious prompts, especially jailbreak attacks, is essential for safe and reliable use. Recently, activation steering has emerged as an effective approach for enhancing LLM safety by adding a refusal...
7.2AI score
SaveExploits0
Citrix CDFControl Service How to Save Logs On A UNC Network Share
Sometimes it may be necessary to save trace data to a shared network folder, for example, crash/hang issues with non-persistent VDAs or due to local disk space constraints...
6.9AI score
SaveExploits0
20