Fine-tuned Model Collections using the "Representation Bending" (REPBEND) approach described in Representation Bending for Large Language Model Safety
AI & ML interests
AI Safety & AI Security
Recent Activity
View all activity
Papers
X-Teaming Evolutionary M2S: Automated Discovery of Multi-turn to Single-turn Jailbreak Templates
ObjexMT: Objective Extraction and Metacognitive Calibration for LLM-as-a-Judge under Multi-Turn Jailbreaks
Organization Card
AIM Intelligence
Securing the Future of AI.
AIM Intelligence is a leading AI safety & security startup dedicated to building safe, reliable, and trustworthy AI . We specialize in automated red teaming and robust defense mechanisms against attacks.
🔗 Connect with Us
- Website: aim-intelligence.com
- LinkedIn: AIM Intelligence
- Contact: [email protected]
datasets
0
None public yet