3 citations · 4 across the 8 of their papers we have counts for
9 papers
Circuit Discovery Helps Detect LLM Jailbreaking: A Mechanistic Interpretability Study
Paria Mehrbod, Boris Knyazev, Guy Wolf +2
Despite extensive safety alignment, large language models (LLMs) remain vulnerable to jailbreak attacks that bypass safeguards to elicit harmful content. While prior work attribute…
Efficient Refusal Ablation in LLM through Optimal Transport
Geraldin Nanfack, Eugene Belilovsky, Elvis Dohmatob
Safety-aligned language models refuse harmful requests through learned refusal behaviors encoded in their internal representations. Recent activation-based jailbreaking methods cir…
Test Time Adaptation Using Adaptive Quantile Recalibration
Paria Mehrbod, Pedro Vianna, Geraldin Nanfack +2
Domain adaptation is a key strategy for enhancing the generalizability of deep learning models in real-world scenarios, where test distributions often diverge significantly from th…
FairDropout: Using Example-Tied Dropout to Enhance Generalization of Minority Groups
Geraldin Nanfack, Eugene Belilovsky
Deep learning models frequently exploit spurious features in training data to achieve low training error, often resulting in poor generalization when faced with shifted testing dis…
Not Only the Last-Layer Features for Spurious Correlations: All Layer Deep Feature Reweighting
Humza Wajid Hameed, Geraldin Nanfack, Eugene Belilovsky
Spurious correlations are a major source of errors for machine learning models, in particular when aiming for group-level fairness. It has been recently shown that a powerful appro…
From Feature Visualization to Visual Circuits: Effect of Adversarial Model Manipulation
Geraldin Nanfack, Michael Eickenberg, Eugene Belilovsky
Understanding the inner working functionality of large-scale deep neural networks is challenging yet crucial in several high-stakes applications. Mechanistic inter- pretability is…
Adversarial Attacks on the Interpretation of Neuron Activation Maximization
Geraldin Nanfack, Alexander Fulleringer, Jonathan Marty +2
The internal functional behavior of trained Deep Neural Networks is notoriously difficult to interpret. Activation-maximization approaches are one set of techniques used to interpr…
An Experimental Investigation into the Evaluation of Explainability Methods
Sédrick Stassin, Alexandre Englebert, Géraldin Nanfack +7
EXplainable Artificial Intelligence (XAI) aims to help users to grasp the reasoning behind the predictions of an Artificial Intelligence (AI) system. Many XAI approaches have emerg…
Squeeze-SegNet: A new fast Deep Convolutional Neural Network for Semantic Segmentation
Geraldin Nanfack, Azeddine Elhassouny, Rachid Oulad Haj Thami
The recent researches in Deep Convolutional Neural Network have focused their attention on improving accuracy that provide significant advances. However, if they were limited to cl…