156 citations · 238 across the 11 of their papers we have counts for
11 papers
Adaptive Nucleus Truncation for Long-Form Reasoning
Ousmane Amadou Dia
Sampling plays an important role in long-form language-model reasoning. Over thousands of decoding steps, small changes in the candidate token set can compound into different reaso…
Variational Proximal Policy Optimization
Ousmane Amadou Dia
Reinforcement Learning from Human Feedback via Proximal Policy Optimization often suffers from policy mode collapse, brittle exploration loops, and distribution drift. This paper i…
LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions
Yang Xu, Xuanming Zhang, Samuel Yeh +4
Deception is a pervasive feature of human communication and an emerging concern in large language models (LLMs). While recent studies document instances of LLM deception, most eval…
On Influence Functions, Classification Influence, Relative Influence, Memorization and Generalization
Michael Kounavis, Ousmane Dia, Ilqar Ramazanli
Machine learning systems such as large scale recommendation systems or natural language processing systems are usually trained on billions of training points and are associated wit…
Training set cleansing of backdoor poisoning by self-supervised representation learning
H. Wang, S. Karami, O. Dia +6
A backdoor or Trojan attack is an important type of data poisoning attack against deep neural network (DNN) classifiers, wherein the training dataset is poisoned with a small numbe…
How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?
Yifei Ming, Yiyou Sun, Ousmane Dia +1
Out-of-distribution (OOD) detection is a critical task for reliable machine learning. Recent advances in representation learning give rise to distance-based OOD detection, where te…
Localized Uncertainty Attacks
Ousmane Amadou Dia, Theofanis Karaletsos, Caner Hazirbas +3
The susceptibility of deep learning models to adversarial perturbations has stirred renewed attention in adversarial examples resulting in a number of attacks. However, most of the…
Enabling Inference Privacy with Adaptive Noise Injection
Sanjay Kariyappa, Ousmane Dia, Moinuddin K Qureshi
User-facing software services are becoming increasingly reliant on remote servers to host Deep Neural Network (DNN) models, which perform inference tasks for the clients. Such serv…
Adversarial Examples in Modern Machine Learning: A Review
Rey Reza Wiyatno, Anqi Xu, Ousmane Dia +1
Recent research has found that many families of machine learning models are vulnerable to adversarial examples: inputs that are specifically designed to cause the target model to p…
Semantics Preserving Adversarial Learning
Ousmane Amadou Dia, Elnaz Barshan, Reza Babanezhad
While progress has been made in crafting visually imperceptible adversarial examples, constructing semantically meaningful ones remains a challenge. In this paper, we propose a fra…
Bayesian Model-Agnostic Meta-Learning
Taesup Kim, Jaesik Yoon, Ousmane Dia +3
Learning to infer Bayesian posterior from a few-shot dataset is an important step towards robust meta-learning due to the model uncertainty inherent in the problem. In this paper,…