Search Results for author:
Found 21 papers, 9 papers with code
Surfacing Privacy Settings Using Semantic Matching
Online services utilize privacy settings to provide users with control over their data.
A Picture is Worth 500 Labels: A Case Study of Demographic Disparities in Local Machine Learning Models for Instagram and TikTok
Capitalizing on this new processing model of locally analyzing user images, we analyze two popular social media apps, TikTok and Instagram, to reveal (1) what insights vision models in both apps infer about users from their image and video data and (2) whether these models exhibit performance disparities with respect to demographics.
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
More recent LLMs often incorporate an additional layer of defense, a Guard Model, which is a second LLM that is designed to check and moderate the output response of the primary LLM.
Do Large Code Models Understand Programming Concepts? A Black-box Approach
Large Language Models' success on text generation has also made them better at code generation and coding tasks.
Human-Producible Adversarial Examples
Visual adversarial examples have so far been restricted to pixel-level image manipulations in the digital world, or have required sophisticated equipment such as 2D or 3D printers to be produced in the physical real world.
Limitations of Face Image Generation
In particular, their ability to synthesize and modify human faces has spurred research into using generated face images in both training data augmentation and model performance assessments.
SEA: Shareable and Explainable Attribution for Query-based Black-box Attacks
Machine Learning (ML) systems are vulnerable to adversarial examples, particularly those from query-based black-box attacks.
Theoretically Principled Trade-off for Stateful Defenses against Query-Based Black-Box Attacks
This work aims to address this gap by offering a theoretical characterization of the trade-off between detection and false positive rates for stateful defenses.
Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks
Such stateful defenses aim to defend against black-box attacks by tracking the query history and detecting and rejecting queries that are "similar" and thus preventing black-box attacks from finding useful gradients and making progress towards finding adversarial attacks within a reasonable query budget.
SkillFence: A Systems Approach to Practically Mitigating Voice-Based Confusion Attacks
Our key insight is that we can interpret a user's intentions by analyzing their activity on counterpart systems of the web and smartphones.
On the Limitations of Stochastic Pre-processing Defenses
An example of such a defense is to apply a random transformation to inputs prior to feeding them to the model.
D4: Detection of Adversarial Diffusion Deepfakes Using Disjoint Ensembles
D4 uses an ensemble of models over disjoint subsets of the frequency spectrum to significantly improve adversarial robustness.
An Exploration of Multicalibration Uniform Convergence Bounds
Given the prevalence of ERM sample complexity bounds, our proposed framework enables machine learning practitioners to easily understand the convergence behavior of multicalibration error for a myriad of classifier architectures.
Tubes Among Us: Analog Attack on Automatic Speaker Identification
Recent years have seen a surge in the popularity of acoustics-enabled personal devices powered by machine learning.
Fairness Properties of Face Recognition and Obfuscation Systems
We answer this question with an analytical and empirical exploration of recent face obfuscation systems.
Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systems
As real-world images come in varying sizes, the machine learning model is part of a larger system that includes an upstream image scaling algorithm.
Face-Off: Adversarial Face Obfuscation
We implement and evaluate Face-Off to find that it deceives three commercial face recognition services from Microsoft, Amazon, and Face++.
Cryptography and Security
Analyzing Accuracy Loss in Randomized Smoothing Defenses
In test-time attacks an adversary crafts adversarial examples, which are specially crafted perturbations imperceptible to humans which, when added to an input example, force a machine learning model to misclassify the given input example.
Rearchitecting Classification Frameworks For Increased Robustness
and how to design a classification paradigm that leverages these invariances to improve the robustness accuracy trade-off?
The Privacy Policy Landscape After the GDPR
In this analysis, we find evidence for positive changes triggered by the GDPR, with the specificity level improving on average.
Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning
Companies, users, researchers, and regulators still lack usable and scalable tools to cope with the breadth and depth of privacy policies.
