1 citations · 1 across the 3 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Adversarial Robustness of Activation Steering in Large Language Models
Kien Le, Thai Le
Activation steering has become a popular training-free method to control LLM behavior by injecting precomputed direction vectors into the model's residual stream at inference time.…
cs.LG2025★ 1 cited
What You Read Isn't What You Hear: Linguistic Sensitivity in Deepfake Speech Detection
Binh Nguyen, Shuji Shi, Ryan Ofman +1
Recent advances in text-to-speech technologies have enabled realistic voice generation, fueling audio-based deepfake attacks such as fraud and impersonation. While audio anti-spoof…