Alexander Panfilov's picture

2 10 2

Alexander Panfilov

kotekjedi

·

AI & ML interests

None yet

Recent Activity

authored a paper 11 days ago

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

upvoted a paper 11 days ago

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

commented on a paper 11 days ago

Adaptive Attacks on Trusted Monitors Subvert AI Control Protocols

View all activity

Organizations

Papers 4

arxiv:2510.09462

arxiv:2509.18058

arxiv:2505.20162

arxiv:2310.05327

models 6

kotekjedi/qwq3-32b-lora-jailbreak-detection-merged

kotekjedi/qwq3-32b-lora-jailbreak-detection

kotekjedi/qwen3-32b-lora-jailbreak-detection_v2

kotekjedi/qwen3-32b-lora-jailbreak-detection-merged_v2

Text Generation • 33B • Updated Sep 15 • 3

kotekjedi/qwen3-32b-lora-jailbreak-detection-merged

Text Generation • 33B • Updated Sep 13 • 3

kotekjedi/qwen3-32b-lora-jailbreak-detection

datasets 0

None public yet