67 citations · 113 across the 11 of their papers we have counts for
12 papers
Visual Memory Attacks Can Persist Through The KV Cache
David Dobre, Leo Schwinn, Gauthier Gidel +3
Modern language model systems operate autonomously over increasingly long contexts containing untrusted text and images. Can an adversarial input continue to steer a model even aft…
A Generative Approach to LLM Harmfulness Mitigation with Red Flag Tokens
David Dobre, Mehrnaz Mofakhami, Sophie Xhonneux +2
Many safety post-training methods for large language models (LLMs) are designed to modify the model's behaviour from producing unsafe answers to issuing refusals. However, such dis…
Learning diverse attacks on large language models for robust red-teaming and safety tuning
Seanie Lee, Minsu Kim, Lynn Cherif +8
Red-teaming, or identifying prompts that elicit harmful responses, is a critical step in ensuring the safe and responsible deployment of large language models (LLMs). Developing ef…
In-Context Learning Can Re-learn Forbidden Tasks
Sophie Xhonneux, David Dobre, Jian Tang +2
Despite significant investment into safety training, large language models (LLMs) deployed in the real world still suffer from numerous vulnerabilities. One perspective on LLM safe…
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
Leo Schwinn, David Dobre, Sophie Xhonneux +2
Current research in adversarial robustness of LLMs focuses on discrete input manipulations in the natural language space, which can be directly transferred to closed-source models.…
Adversarial Attacks and Defenses in Large Language Models: Old and New Threats
Leo Schwinn, David Dobre, Stephan Günnemann +1
Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment h…
Raising the Bar for Certified Adversarial Robustness with Diffusion Models
Thomas Altstidl, David Dobre, Björn Eskofier +2
Certified defenses against adversarial attacks offer formal guarantees on the robustness of a model, making them more reliable than empirical methods such as adversarial training,…
Sarah Frank-Wolfe: Methods for Constrained Optimization with Best Rates and Practical Features
Aleksandr Beznosikov, David Dobre, Gauthier Gidel
The Frank-Wolfe (FW) method is a popular approach for solving optimization problems with structured constraints that arise in machine learning applications. In recent years, stocha…
Dissecting adaptive methods in GANs
Samy Jelassi, David Dobre, Arthur Mensch +2
Adaptive methods are a crucial component widely used for training generative adversarial networks (GANs). While there has been some work to pinpoint the "marginal value of adaptive…
Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise
Eduard Gorbunov, Marina Danilova, David Dobre +3
Stochastic first-order methods such as Stochastic Extragradient (SEG) or Stochastic Gradient Descent-Ascent (SGDA) for solving smooth minimax problems and, more generally, variatio…
Echoes from the scattering of wavepackets on wormholes
José T. Gálvez Ghersi, Andrei V. Frolov, David A. Dobre
It has been recently shown that observing pulses isolated from the gravitational radiation transient (also known as echoes) would prove the existence of exotic compact objects (ECO…
Unbraiding the Bounce: Superluminality around the Corner
David A. Dobre, Andrei V. Frolov, José T. Gálvez Ghersi +2
We study a particular realization of the cosmological bounce scenario proposed recently by Ijjas and Steinhardt. First, we find that their bouncing solution starts from a divergent…