NeurIPS 2024PastOther
The Third Workshop on New Frontiers in Adversarial Machine Learning
AdvML-Frontiers 2024
- Submission deadline
- Aug 31, 2024, 13:05 UTCimported from OpenReview — check the website for extensions
- Submission portal
- OpenReview
- Notes
- Topics were auto-suggested and may be imprecise — edits welcome.
Accepted papers (37)
Fetched from OpenReview (v2) on 2026-06-10.
Achieving Domain-Independent Certified Robustness via Knowledge Continuity
AdjointDEIS: Efficient Gradients for Diffusion Models
Advancing NLP Security by Leveraging LLMs as Adversarial Engines
Adversarial Bounding Boxes Generation (ABBG) Attack against Visual Object Trackers
Adversarial Databases Improve Success in Retrieval-based Large Language Models
Adversarial Training based Domain Adaptation for Cross-Subject Emotion Recognition
Adversarial Watermarking for Face Recognition
An Adversarial Learning Approach to Irregular Time-Series Forecasting
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations
dSTAR: Straggler Tolerant and Byzantine Resilient Distributed SGD
Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness
Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targetted Object Removal from Images
Imitation Guided Automated Red Teaming
In Search of the $\textit{Successful}$ Interpolation: On the Role of $\textit{Sharpness}$ in CLIP Generalization
In-distribution adversarial attacks on object recognition models using gradient-free search.
Jailbreak Defense in a Narrow Domain: Failures of existing methods and Improving Transcript-Based Classifiers
Learning From Convolution-based Unlearnable Datasets
Learning to Forget using Hypernetworks
LLM-PIRATE: A benchmark for indirect prompt injection attacks in Large Language Models
Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference
Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment
Provable Robustness of (Graph) Neural Networks Against Data Poisoning and Backdoor Attacks
RenderAttack: Hundreds of Adversarial Attacks Through Differentiable Texture Generation
Rethinking Backdoor Detection Evaluation for Language Models
Rethinking Randomized Smoothing from the Perspective of Scalability
Robustness of Practical Perceptual Hashing Algorithms to Hash-Evasion and Hash-Inversion Attacks
SkipOOD: Efficient Out-of-Distribution Input Detection using Skipping Mechanism
Smoothing-Based Adversarial Defense Methods for Inverse Problems
Sparse patches adversarial attacks via extrapolating point-wise information
Sparse Transfer Learning Accelerates and Enhances Certified Robustness: A Comprehensive Study
The Ultimate Cookbook for Invisible Poison: Crafting Subtle Clean-Label Text Backdoors with Style Attributes
Track 1: Robust Offline Learning via Adversarial World Models
TrackPGD: Efficient Adversarial Attack using Object Binary Masks against Robust Transformer Trackers
Unveiling Synthetic Faces: How Synthetic Datasets Can Expose Real Identities
vTune: Verifiable Fine-Tuning Through Backdooring
When Do Universal Image Jailbreaks Transfer Between Vision-Language Models?