Search Results for author:
Found 25 papers, 10 papers with code
WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks
In order to better focus adversarial research, we construct a new benchmark called WASP (Web Agent Security against Prompt injection attacks) that introduces realistic web agent hijacking objectives and an isolated environment to test them in that does not affect real users or the live web.
AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents
In this work, we propose one way to address that potential risk, by training AI agents to better satisfy the privacy principle of data minimization.
AdvPrefix: An Objective for Nuanced LLM Jailbreaks
To address these limitations, we introduce AdvPrefix, a new prefix-forcing objective that enables more nuanced control over model behavior while being easy to optimize.
Persistent Pre-Training Poisoning of LLMs
Our work evaluates for the first time whether language models can also be compromised during pre-training, with a focus on the persistence of pre-training attacks after models are fine-tuned as helpful and harmless chatbots (i. e., after SFT and DPO).
Gradient-based Jailbreak Images for Multimodal Fusion Models
Augmenting language models with image inputs may enable more effective jailbreak attacks through continuous optimization, unlike text inputs that require discrete optimization.
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
Question Answering
on PeerQA
Uncertainty-Based Abstention in LLMs Improves Safety and Reduces Hallucinations
A major barrier towards the practical deployment of large language models (LLMs) is their lack of reliability.
Towards Red Teaming in Multimodal and Multilingual Translation
Assessing performance in Natural Language Processing is becoming increasingly complex.
Seamless: Multilingual Expressive and Streaming Speech Translation
In this work, we introduce a family of models that enable end-to-end expressive and multilingual translations in a streaming fashion.
automatic-speech-translation
Multimodal Machine Translation
+2
Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models
This paper presents CyberSecEval, a comprehensive benchmark developed to help bolster the cybersecurity of Large Language Models (LLMs) employed as coding assistants.
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 #37 on
Code Generation
on MBPP
(using extra training data)
You Only Need a Good Embeddings Extractor to Fix Spurious Correlations
With experiments on a wide range of pre-trained models and pre-training datasets, we show that the capacity of the pre-training model and the size of the pre-training dataset matters.
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
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
Equipped with ImageNet-X, we investigate 2, 200 current recognition models and study the types of mistakes as a function of model's (1) architecture, e. g. transformer vs. convolutional, (2) learning paradigm, e. g. supervised vs. self-supervised, and (3) training procedures, e. g., data augmentation.
Adversarial Text Normalization
Additionally, the process to retrain a model is time and resource intensive, creating a need for a lightweight, reusable defense.
Disrupting Model Training with Adversarial Shortcuts
When data is publicly released for human consumption, it is unclear how to prevent its unauthorized usage for machine learning purposes.
FoggySight: A Scheme for Facial Lookup Privacy
Searches in these databases are now being offered as a service to law enforcement and others and carry a multitude of privacy risks for social media users.
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.
Security and Machine Learning in the Real World
Machine learning (ML) models deployed in many safety- and business-critical systems are vulnerable to exploitation through adversarial examples.
Physical Adversarial Examples for Object Detectors
In this work, we extend physical attacks to more challenging object detection models, a broader class of deep learning algorithms widely used to detect and label multiple objects within a scene.
Robust Physical-World Attacks on Deep Learning Visual Classification
Recent studies show that the state-of-the-art deep neural networks (DNNs) are vulnerable to adversarial examples, resulting from small-magnitude perturbations added to the input.
Note on Attacking Object Detectors with Adversarial Stickers
Given the fact that state-of-the-art objection detection algorithms are harder to be fooled by the same set of adversarial examples, here we show that these detectors can also be attacked by physical adversarial examples.
Robust Physical-World Attacks on Deep Learning Models
We propose a general attack algorithm, Robust Physical Perturbations (RP2), to generate robust visual adversarial perturbations under different physical conditions.
