activity
20242026
collaborators

8 papers

cs.CY2026

Human-Provenance Verification should be Treated as Labor Infrastructure in AI-Saturated Markets

Erin McGurk, David Khachaturov

We argue that AI-saturated markets are likely to create Veblen-good premiums, which we term human-provenance premiums, for verified human presence, and hence AI governance should t…

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.CR2025

Scaling Trends for Data Poisoning in LLMs

Dillon Bowen, Brendan Murphy, Will Cai +3

LLMs produce harmful and undesirable behavior when trained on datasets containing even a small fraction of poisoned data. We demonstrate that GPT models remain vulnerable to fine-t…

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…