Meta AI

188 results for "adversarial"

Publication

November 20, 2024

Conversational AI

Computer Vision

Llama Guard 3 Vision: Safeguarding Human-AI Image Understanding Conversations

Jianfeng Chi, Ujjwal Karn, Hongyuan Zhan, Eric Smith, Javier Rando, Yiming Zhang, Kate Plawiak, Zacharie Delpierre Coudert, Kartikeya Upasani, Mahesh Pasupuleti

November 20, 2024

Read the Paper

Publication

April 30, 2024

Reinforcement Learni9ng

Multi-Agent Diagnostics for Robustness via Illuminated Diversity

Mikayel Samvelyan, Minqi Jiang, Davide Paglieri, Jack Parker-Holder, Tim Rocktäschel

April 30, 2024

Read the Paper

Publication

April 05, 2024

Conversational AI

NLP

MART: Improving LLM Safety with Multi-round Automatic Red-Teaming

Suyu Ge, Chunting Zhou, Rui Hou, Madian Khabsa, Yi-Chia Wang, Qifan Wang, Jiawei Han, Yuning Mao

April 05, 2024

Read the Paper

Publication

March 14, 2024

Computer Vision

Towards image compression with perfect realism at ultra-low bitrates

Marlene Careil, Matthew Muckley, Jakob Verbeek, Stephane Lathuiliere

March 14, 2024

Read the Paper

Publication

January 25, 2024

Computer Vision

LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks

Felix Xu, Di Lin, Jianjun Zhao, Jianlang Chen, Lei Ma, Qing Guo, Wei Feng, Xuhong Ren

January 25, 2024

Read the Paper

Publication

November 28, 2023

NLP

ROAST: Robustifying Language Models via Adversarial Perturbation with Selective Training

Jaehyung Kim, Yuning Mao, Rui Hou, Hanchao Yu, Davis Liang, Pascale Fung, Qifan Wang, Fuli Feng, Lifu Huang, Madian Khabsa

November 28, 2023

Read the Paper

Publication

October 28, 2023

Computer Vision

ALA: Naturalness-aware Adversarial Lightness Attack

Felix Xu, Geguang Pu, Jiayi Zhu, Jincao Feng, Liangru Sun, Qing Guo, Yang Liu, Yihao Huang

October 28, 2023

Read the Paper

Publication

September 28, 2023

Computer Vision

Among Us: Adversarially Robust Collaborative Perception by Consensus

Yiming Li, Qi Fang, Jiamu Bai, Siheng Chen, Felix Xu, Chen Feng

September 28, 2023

Read the Paper

Publication

April 24, 2023

Reinforcement Learni9ng

Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning

David Wu, Adam Lerer, Jonathan Gray, Athul Paul Jacob, Gabriele Farina, Alexander Miller, Noam Brown

April 24, 2023

Read the Paper

Publication

February 21, 2023

Computer Vision

Core Machine Learning

ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networks

Felix Xu, Fuyuan Zhang, Hua Qi, Jianjun Zhao, Jianlang Chen, Lei Ma, Qing Guo, Zhijie Wang

February 21, 2023

Read the Paper

Publication

July 18, 2022

Adversarial Text Normalization

Joanna Bitton, Ivan Evtimov, Maya Pavlova

July 18, 2022

Read the Paper

Publication

December 05, 2021

Integrity

Core Machine Learning

BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining

Weizhe Hua, Yichi Zhang, Chuan Guo, Zhiru Zhang, Edward Suh

December 05, 2021

Read the Paper

Person

Caner Hazirbas

Seattle, United States

Caner is a Research Scientist in the AI Red Team at Facebook AI Applied Research. He received his Ph.D. and Masters from the Technical University of Mu...

Research Area:

Core Machine Learning

Computer Vision

Person

Cristian Canton Ferrer

Seattle, United States

Cristian is a Research Scientist Manager on the AI Integrity Team at Facebook AI Applied Research. His research interests lie in the field of computer v...

Research Area:

NLP

Core Machine Learning

Person

Joanna Bitton

Seattle, United States

Joanna is a Software Engineer in the AI Red Team at Facebook AI Applied Research. She received her Masters in Computer Science from the Courant Institu...

Research Area:

NLP

Core Machine Learning

Person

Kevin J Liang

Menlo Park, United States

Kevin is a Research Scientist at Facebook AI Applied Research (FAIR). His research interests are primarily in deep learning, particularly computer visio...

Research Area:

Computer Vision

Person

Maziar Sanjabi

Menlo Park, United States

Maziar is a research scientist on the AI Integrity team. AI integrity strives to make the world a better place by tackling important problems, such as h...

Research Area:

Core Machine Learning

Integrity

Blog

April 17, 2025

Open Source

Advancing AI systems through progress in perception, localization, and reasoning

Meta FAIR is releasing several new research artifacts that advance our understanding of perception and support our goal of achieving advanced machine intelligence (AMI).

April 17, 2025

Learn More

Blog

April 05, 2025

Open Source

The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation

We’re introducing Llama 4 Scout and Llama 4 Maverick, the first open-weight natively multimodal models with unprecedented context support and our first built using a mixture-of-experts (MoE) architecture.

April 05, 2025

Learn More

Blog

July 18, 2023

Research

Meta and Microsoft Introduce the Next Generation of Llama

We’re introducing the availability of Llama 2, the next generation of our open source large language model.

July 18, 2023

Learn More

Blog

August 24, 2023

Developer Tools

NLP

Introducing Code Llama, a state-of-the-art large language model for coding

Code Llama, which is built on top of Llama 2, is free for research and commercial use.

August 24, 2023

Learn More

Blog

December 04, 2023

Research

Open Source

Introducing the AI Alliance

AI Alliance Launches as an International Community of Leading Technology Developers, Researchers, and Adopters Collaborating Together to Advance Open, Safe, Responsible AI

December 04, 2023

Learn More

Blog

April 18, 2024

Open Source

Introducing Meta Llama 3: The most capable openly available LLM to date

Today, we’re introducing Meta Llama 3, the next generation of our state-of-the-art open source large language model. In the coming months, we expect to share new capabilities, additional model sizes, and more.

April 18, 2024

Learn More

Blog

April 18, 2024

Open Source

Our responsible approach to Meta AI and Meta Llama 3

We’ve taken responsible steps before launching Meta AI and Meta Llama 3 so people can have safer and more enjoyable experiences.

April 18, 2024

Learn More

Blog

December 07, 2023

Developer Tools

Research

Announcing Purple Llama: Towards open trust and safety in the new world of generative AI

Meta AI announces Purple Llama, a project for open trust and safety in generative AI, with tools for cybersecurity and input/output filtering.

December 07, 2023

Learn More

Blog

July 23, 2024

Open Source

Expanding our open source large language models responsibly

Today, we’re sharing the measures and safeguards we’ve taken to responsibly scale the Llama 3.1 collection of models, including the 405B.

July 23, 2024

Learn More

Blog

September 25, 2024

Open Source

Connect 2024: The responsible approach we’re taking to generative AI

With the rapidly evolving AI landscape, we recognize the importance of sharing our responsibility and safety approach with everyone.

September 25, 2024

Learn More

Blog

December 12, 2024

Open Source

Sharing new research, models, and datasets from Meta FAIR

Meta FAIR is releasing new research artifacts that highlight our recent innovations in developing agents, robustness and safety, and architectures that facilitate machine learning.