collaborators

5 papers

cs.CL2026

Controllable and explainable personality sliders for LLMs at inference time

Florian Hoppe, David Khachaturov, Robert Mullins +1

Aligning Large Language Models (LLMs) with specific personas typically relies on expensive and monolithic Supervised Fine-Tuning (SFT) or RLHF. While effective, these methods requi…

cs.SI2026

Tiered Anonymity on Social-Media Platforms as a Countermeasure against Deepfakes and LLM-Driven Mass Misinformation

David Khachaturov, Roxanne Schnyder, Robert Mullins

We argue that governments should mandate a three-tier anonymity framework on social-media platforms as a reactionary measure prompted by the ease-of-production of deepfakes and lar…

cs.LG2025

"I am bad": Interpreting Stealthy, Universal and Robust Audio Jailbreaks in Audio-Language Models

Isha Gupta, David Khachaturov, Robert Mullins

The rise of multimodal large language models has introduced innovative human-machine interaction paradigms but also significant challenges in machine learning safety. Audio-Languag…

cs.LG2025

Adversarial Suffix Filtering: a Defense Pipeline for LLMs

David Khachaturov, Robert Mullins

Large Language Models (LLMs) are increasingly embedded in autonomous systems and public-facing environments, yet they remain susceptible to jailbreak vulnerabilities that may under…

cs.LG2025

Watermarking Needs Input Repetition Masking

David Khachaturov, Robert Mullins, Ilia Shumailov +1

Recent advancements in Large Language Models (LLMs) raised concerns over potential misuse, such as for spreading misinformation. In response two counter measures emerged: machine l…