2 citations · 6 across the 19 of their papers we have counts for
6 papers · 1 filter
LLM Wardens: Mitigating Adversarial Persuasion with Third-Party Conversational Oversight
Lennart Wachowiak, Scott D. Blain, David Williams-King +1
LLMs are increasingly capable of persuasion, which raises the question of how to protect users against manipulation. In a preregistered user study (N=120) across four decision-maki…
Full-Stack Alignment: Co-Aligning AI and Institutions with Thick Models of Value
Joe Edelman, Tan Zhi-Xuan, Ryan Lowe +30
Beneficial societal outcomes cannot be guaranteed by aligning individual AI systems with the intentions of their operators or users. Even an AI system that is perfectly aligned to…
LLM Agents Are the Antidote to Walled Gardens
Samuele Marro, Philip Torr
While the Internet's core infrastructure was designed to be open and universal, today's application layer is dominated by closed, proprietary platforms. Open and interoperable APIs…
Code Simulation as a Proxy for High-order Tasks in Large Language Models
Emanuele La Malfa, Christoph Weinhuber, Orazio Torre +6
Many reasoning, planning, and problem-solving tasks share an intrinsic algorithmic nature: correctly simulating each step is a sufficient condition to solve them correctly. We coll…
Jailbreaking Large Language Models in Infinitely Many Ways
Oliver Goldstein, Emanuele La Malfa, Felix Drinkall +2
We discuss the ``Infinitely Many Paraphrases'' attacks (IMP), a category of jailbreaks that leverages the increasing capabilities of a model to handle paraphrases and encoded commu…
Computational Asymmetries in Robust Classification
Samuele Marro, Michele Lombardi
In the context of adversarial robustness, we make three strongly related contributions. First, we prove that while attacking ReLU classifiers is -hard, ensuring their…