Search Results for author:
Found 32 papers, 11 papers with code
Automated Red Teaming with GOAT: the Generative Offensive Agent Tester
Common users of AI models may not have advanced knowledge of adversarial machine learning methods or access to model internals, and they do not spend a lot of time crafting a single highly effective adversarial prompt.
The Llama 3 Herd of Models
This paper presents a new set of foundation models, called Llama 3.
Ranked #3 on
Multi-task Language Understanding
on MMLU
Fairness-Aware Meta-Learning via Nash Bargaining
To address issues of group-level fairness in machine learning, it is natural to adjust model parameters based on specific fairness objectives over a sensitive-attributed validation set.
Towards Red Teaming in Multimodal and Multilingual Translation
Assessing performance in Natural Language Processing is becoming increasingly complex.
On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms
However, machine and deep learning algorithms, popular in the AI community today, depend heavily on the data used during their development.
VPA: Fully Test-Time Visual Prompt Adaptation
Inspired by the success of textual prompting, several studies have investigated the efficacy of visual prompt tuning.
Code Llama: Open Foundation Models for Code
We release Code Llama, a family of large language models for code based on Llama 2 providing state-of-the-art performance among open models, infilling capabilities, support for large input contexts, and zero-shot instruction following ability for programming tasks.
Ranked #36 on
Code Generation
on MBPP
Llama 2: Open Foundation and Fine-Tuned Chat Models
In this work, we develop and release Llama 2, a collection of pretrained and fine-tuned large language models (LLMs) ranging in scale from 7 billion to 70 billion parameters.
Ranked #2 on
Question Answering
on PubChemQA
Data-Driven but Privacy-Conscious: Pedestrian Dataset De-identification via Full-Body Person Synthesis
To highlight the importance of privacy issues and motivate future research, we motivate and introduce the Pedestrian Dataset De-Identification (PDI) task.
The Casual Conversations v2 Dataset
This paper introduces a new large consent-driven dataset aimed at assisting in the evaluation of algorithmic bias and robustness of computer vision and audio speech models in regards to 11 attributes that are self-provided or labeled by trained annotators.
A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others
Key to advancing the reliability of vision systems is understanding whether existing methods can overcome multiple shortcuts or struggle in a Whac-A-Mole game, i. e., where mitigating one shortcut amplifies reliance on others.
Ranked #1 on
Out-of-Distribution Generalization
on ImageNet-W
Casual Conversations v2: Designing a large consent-driven dataset to measure algorithmic bias and robustness
Developing robust and fair AI systems require datasets with comprehensive set of labels that can help ensure the validity and legitimacy of relevant measurements.
Generating High Fidelity Data from Low-density Regions using Diffusion Models
We observe that uniform sampling from diffusion models predominantly samples from high-density regions of the data manifold.
Results and findings of the 2021 Image Similarity Challenge
The 2021 Image Similarity Challenge introduced a dataset to serve as a new benchmark to evaluate recent image copy detection methods.
Localized Uncertainty Attacks
Under this threat model, we create adversarial examples by perturbing only regions in the inputs where a classifier is uncertain.
The 2021 Image Similarity Dataset and Challenge
This benchmark is used for the Image Similarity Challenge at NeurIPS'21 (ISC2021).
Ranked #1 on
Image Similarity Detection
on DISC21 dev
Towards Measuring Fairness in AI: the Casual Conversations Dataset
The videos were recorded in multiple U. S. states with a diverse set of adults in various age, gender and apparent skin tone groups.
Adversarial Evaluation of Multimodal Models under Realistic Gray Box Assumption
This work examines the vulnerability of multimodal (image + text) models to adversarial threats similar to those discussed in previous literature on unimodal (image- or text-only) models.
Adversarial Threats to DeepFake Detection: A Practical Perspective
We perform our evaluations on the winning entries of the DeepFake Detection Challenge (DFDC) and demonstrate that they can be easily bypassed in a practical attack scenario by designing transferable and accessible adversarial attacks.
Adversarial collision attacks on image hashing functions
Hashing images with a perceptual algorithm is a common approach to solving duplicate image detection problems.
Preserving Integrity in Online Social Networks
Online social networks provide a platform for sharing information and free expression.
The DeepFake Detection Challenge (DFDC) Dataset
In addition to Deepfakes, a variety of GAN-based face swapping methods have also been published with accompanying code.
Deep Poisoning: Towards Robust Image Data Sharing against Visual Disclosure
Due to respectively limited training data, different entities addressing the same vision task based on certain sensitive images may not train a robust deep network.
The Deepfake Detection Challenge (DFDC) Preview Dataset
In this paper, we introduce a preview of the Deepfakes Detection Challenge (DFDC) dataset consisting of 5K videos featuring two facial modification algorithms.
Hate Speech in Pixels: Detection of Offensive Memes towards Automatic Moderation
This work addresses the challenge of hate speech detection in Internet memes, and attempts using visual information to automatically detect hate speech, unlike any previous work of our knowledge.
Eye In-Painting with Exemplar Generative Adversarial Networks
This paper introduces a novel approach to in-painting where the identity of the object to remove or change is preserved and accounted for at inference time: Exemplar GANs (ExGANs).
Social Style Characterization from Egocentric Photo-streams
This paper proposes a system for automatic social pattern characterization using a wearable photo-camera.
Towards social pattern characterization in egocentric photo-streams
Following the increasingly popular trend of social interaction analysis in egocentric vision, this manuscript presents a comprehensive study for automatic social pattern characterization of a wearable photo-camera user, by relying on the visual analysis of egocentric photo-streams.
Disentangling Motion, Foreground and Background Features in Videos
This paper introduces an unsupervised framework to extract semantically rich features for video representation.
SalGAN: Visual Saliency Prediction with Generative Adversarial Networks
We introduce SalGAN, a deep convolutional neural network for visual saliency prediction trained with adversarial examples.
Training Deep Networks for Facial Expression Recognition with Crowd-Sourced Label Distribution
Crowd sourcing has become a widely adopted scheme to collect ground truth labels.
Facial Expression Recognition
Facial Expression Recognition (FER)
+1
Learning by tracking: Siamese CNN for robust target association
This paper introduces a novel approach to the task of data association within the context of pedestrian tracking, by introducing a two-stage learning scheme to match pairs of detections.
