research
∙
09/12/2023
Certified Robust Models with Slack Control and Large Lipschitz Constants
Despite recent success, state-of-the-art learning-based models remain hi...
share
research
∙
08/02/2023
A Large-Scale Study of Phishing PDF Documents
Phishing PDFs are malicious PDF documents that do not embed malware but ...
research
∙
07/16/2023
MargCTGAN: A "Marginally” Better CTGAN for the Low Sample Regime
The potential of realistic and useful synthetic data is significant. How...
research
∙
06/19/2023
B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers
We present a new direction for increasing the interpretability of deep n...
research
∙
06/08/2023
From Bad to Worse: Using Private Data to Propagate Disinformation on Online Platforms with a Greater Efficiency
We outline a planned experiment to investigate if personal data (e.g., d...
research
∙
05/24/2023
Private and Collaborative Kaplan-Meier Estimators
Kaplan-Meier estimators capture the survival behavior of a cohort. They ...
research
∙
03/07/2023
Client-specific Property Inference against Secure Aggregation in Federated Learning
Federated learning has become a widely used paradigm for collaboratively...
research
∙
02/23/2023
More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models
We are currently witnessing dramatic advances in the capabilities of Lar...
research
∙
02/15/2023
Data Forensics in Diffusion Models: A Systematic Analysis of Membership Privacy
In recent years, diffusion models have achieved tremendous success in th...
research
∙
02/08/2023
Systematically Finding Security Vulnerabilities in Black-Box Code Generation Models
Recently, large language models for code generation have achieved breakt...
research
∙
02/02/2023
Fed-GLOSS-DP: Federated, Global Learning using Synthetic Sets with Record Level Differential Privacy
This work proposes Fed-GLOSS-DP, a novel approach to privacy-preserving ...
research
∙
01/20/2023
Holistically Explainable Vision Transformers
Transformers increasingly dominate the machine learning landscape across...
research
∙
11/07/2022
Private Set Generation with Discriminative Information
Differentially private data generation techniques have become a promisin...
research
∙
10/10/2022
SimSCOOD: Systematic Analysis of Out-of-Distribution Behavior of Source Code Models
While large code datasets have become available in recent years, acquiri...
research
∙
09/07/2022
Fact-Saboteurs: A Taxonomy of Evidence Manipulation Attacks against Fact-Verification Systems
Mis- and disinformation are now a substantial global threat to our secur...
research
∙
07/12/2022
RelaxLoss: Defending Membership Inference Attacks without Losing Utility
As a long-term threat to the privacy of training data, membership infere...
research
∙
05/20/2022
B-cos Networks: Alignment is All We Need for Interpretability
We present a new direction for increasing the interpretability of deep n...
research
∙
02/08/2022
Practical Challenges in Differentially-Private Federated Survival Analysis of Medical Data
Survival analysis or time-to-event analysis aims to model and predict th...
research
∙
11/30/2021
Open-Domain, Content-based, Multi-modal Fact-checking of Out-of-Context Images via Online Resources
Misinformation is now a major problem due to its potential high risks to...
research
∙
10/11/2021
ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Training
Federated learning is a powerful distributed learning scheme that allows...
research
∙
09/27/2021
Optimising for Interpretability: Convolutional Dynamic Alignment Networks
We introduce a new family of neural network models called Convolutional ...
research
∙
08/25/2021
Backdoor Attacks on Network Certification via Data Poisoning
Certifiers for neural networks have made great progress towards provable...
research
∙
06/22/2021
Euro-PVI: Pedestrian Vehicle Interactions in Dense Urban Centers
Accurate prediction of pedestrian and bicyclist paths is integral to the...
research
∙
05/29/2021
Beyond the Spectrum: Detecting Deepfakes via Re-Synthesis
The rapid advances in deep generative models over the past years have le...
research
∙
03/31/2021
Convolutional Dynamic Alignment Networks for Interpretable Classifications
We introduce a new family of neural network models called Convolutional ...
research
∙
02/09/2021
"What's in the box?!": Deflecting Adversarial Attacks by Randomly Deploying Adversarially-Disjoint Models
Machine learning models are now widely deployed in real-world applicatio...
research
∙
02/04/2021
ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models
Inference attacks against Machine Learning (ML) models allow adversaries...
research
∙
12/16/2020
Responsible Disclosure of Generative Models Using Scalable Fingerprinting
Over the past six years, deep generative models have achieved a qualitat...
research
∙
12/15/2020
CosSGD: Nonlinear Quantization for Communication-efficient Federated Learning
Federated learning facilitates learning across clients without transferr...
research
∙
11/28/2020
Hijack-GAN: Unintended-Use of Pretrained, Black-Box GANs
While Generative Adversarial Networks (GANs) show increasing performance...
research
∙
09/21/2020
Haar Wavelet based Block Autoregressive Flows for Trajectories
Prediction of trajectories such as that of pedestrians is crucial to the...
research
∙
09/18/2020
Synthetic Convolutional Features for Improved Semantic Segmentation
Recently, learning-based image synthesis has enabled to generate high-re...
research
∙
09/07/2020
Adversarial Watermarking Transformer: Towards Tracing Text Provenance with Data Hiding
Recent advances in natural language generation have introduced powerful ...
research
∙
09/01/2020
Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries
Machine learning models have been shown to leak information violating th...
research
∙
07/16/2020
Artificial GAN Fingerprints: Rooting Deepfake Attribution in Training Data
Photorealistic image generation is progressing rapidly and has reached a...
research
∙
06/18/2020
IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis
In this work, we investigate the problem of revealing the functionality ...
research
∙
06/15/2020
GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generators
The wide-spread availability of rich data has fueled the growth of machi...
research
∙
05/20/2020
InfoScrub: Towards Attribute Privacy by Targeted Obfuscation
Personal photos of individuals when shared online, apart from exhibiting...
research
∙
04/08/2020
Normalizing Flows with Multi-Scale Autoregressive Priors
Flow-based generative models are an important class of exact inference m...
research
∙
04/07/2020
Long-Tailed Recognition Using Class-Balanced Experts
Classic deep learning methods achieve impressive results in image recogn...
research
∙
04/07/2020
Inclusive GAN: Improving Data and Minority Coverage in Generative Models
Generative Adversarial Networks (GANs) have brought about rapid progress...
research
∙
12/20/2019
Segmentations-Leak: Membership Inference Attacks and Defenses in Semantic Image Segmentation
Today's success of state of the art methods for semantic segmentation is...
research
∙
12/16/2019
Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing
Despite significant success in Visual Question Answering (VQA), VQA mode...
research
∙
09/27/2019
"Best-of-Many-Samples" Distribution Matching
Generative Adversarial Networks (GANs) can achieve state-of-the-art samp...
research
∙
09/09/2019
GAN-Leaks: A Taxonomy of Membership Inference Attacks against GANs
In recent years, the success of deep learning has carried over from disc...
research
∙
09/01/2019
WhiteNet: Phishing Website Detection by Visual Whitelists
Phishing websites aiming at stealing users' information by claiming fake...
research
∙
08/24/2019
Conditional Flow Variational Autoencoders for Structured Sequence Prediction
Prediction of future states of the environment and interacting agents is...
research
∙
07/25/2019
Interpretability Beyond Classification Output: Semantic Bottleneck Networks
Today's deep learning systems deliver high performance based on end-to-e...
research
∙
06/26/2019
Prediction Poisoning: Utility-Constrained Defenses Against Model Stealing Attacks
With the advances of ML models in recent years, we are seeing an increas...
research
∙
06/24/2019