Prashant Kulkarni
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Crypto×2AI×2NLP×1
Frequent co-authors
Research Timeline
2026
An Independent Safety Evaluation of Kimi K2.5
The paper conducts a preliminary safety evaluation of the open-weight LLM Kimi K2.5, finding that while it is highly capable, it exhibits concerning dual-use risks, particularly regarding CBRNE misuse and disinformation, and recommends mandatory safety testing for future open-weight models.
Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection
The paper introduces 'adversarial restlessness,' an activation-level signature in LLM residual streams, to detect multi-turn prompt injection attacks with high accuracy.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.AIRecentApr 30, 2026
Latent Adversarial Detection: Adaptive Probing of LLM Activations for Multi-Turn Attack Detection
The paper introduces 'adversarial restlessness,' an activation-level signature in LLM residual streams, to detect multi-turn prompt injection attacks with high accuracy.
View →
cs.CRcs.AIcs.CLRecentApr 3, 2026