NeurIPS 2024 Workshop AdvML-Frontiers Submissions

Ensemble everything everywhere: Multi-scale aggregation for adversarial robustness
Stanislav Fort, Balaji Lakshminarayanan
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Rethinking Randomized Smoothing from the Perspective of Scalability
Sukrit Jindal, Devansh Bhardwaj, Anupriya Kumari
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
The Ultimate Cookbook for Invisible Poison: Crafting Subtle Clean-Label Text Backdoors with Style Attributes
Wencong You, Daniel Lowd
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
An Adversarial Learning Approach to Irregular Time-Series Forecasting
Heejeong Nam, Jihyun Kim, Jimin Yeom
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Track 1: Robust Offline Learning via Adversarial World Models
Uljad Berdica, Kelvin Li, Michael Beukman, Alexander David Goldie, Perla Maiolino, Jakob Nicolaus Foerster
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data?
Michael-Andrei Panaitescu-Liess, Zora Che, Bang An, Yuancheng Xu, Pankayaraj Pathmanathan, Souradip Chakraborty, Sicheng Zhu, Tom Goldstein, Furong Huang
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
vTune: Verifiable Fine-Tuning Through Backdooring
Eva Zhang, Akilesh Potti, Micah Goldblum
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Rethinking Backdoor Detection Evaluation for Language Models
Jun Yan, Wenjie Jacky Mo, Xiang Ren, Robin Jia
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Learning From Convolution-based Unlearnable Datasets
Dohyun Kim, Pedro Sandoval-Segura
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Achieving Domain-Independent Certified Robustness via Knowledge Continuity
Alan Sun, Chiyu Ma, Kenneth Ge, Soroush Vosoughi
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Smoothing-Based Adversarial Defense Methods for Inverse Problems
Yang Sun, Jonathan Scarlett
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
LLM-PIRATE: A benchmark for indirect prompt injection attacks in Large Language Models
Anil Ramakrishna, Jimit Majmudar, Rahul Gupta, Devamanyu Hazarika
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Jailbreak Defense in a Narrow Domain: Failures of existing methods and Improving Transcript-Based Classifiers
Tony Tong Wang, John Hughes, Henry Sleight, Rylan Schaeffer, Rajashree Agrawal, Fazl Barez, Mrinank Sharma, Jesse Mu, Nir N Shavit, Ethan Perez
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
RenderAttack: Hundreds of Adversarial Attacks Through Differentiable Texture Generation
Dron Hazra, Alex Bie, Mantas Mazeika, Xuwang Yin, Andy Zou, Dan Hendrycks, Maximilian Kaufmann
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
In Search of the $\textit{Successful}$ Interpolation: On the Role of $\textit{Sharpness}$ in CLIP Generalization
Alireza Abdollahpourrostam
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Hiding-in-Plain-Sight (HiPS) Attack on CLIP for Targetted Object Removal from Images
Arka Daw, Megan Hong-Thanh Chung, Maria Mahbub, Amir Sadovnik
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Learning to Forget using Hypernetworks
Jose Miguel Lara Rangel, Usman Anwar, Stefan Schoepf, Jack Foster, David Krueger
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
In-distribution adversarial attacks on object recognition models using gradient-free search.
Spandan Madan, Tomotake Sasaki, Tzu-Mao Li, Hanspeter Pfister, Xavier Boix
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
SkipOOD: Efficient Out-of-Distribution Input Detection using Skipping Mechanism
Mirazul Haque, Natraj Raman, Petr Babkin, Armineh Nourbakhsh, Xiaomo Liu
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Sparse patches adversarial attacks via extrapolating point-wise information
Yaniv Nemcovsky, Avi Mendelson, Chaim Baskin
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Advancing NLP Security by Leveraging LLMs as Adversarial Engines
Sudarshan Srinivasan, Maria Mahbub, Amir Sadovnik
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Robustness of Practical Perceptual Hashing Algorithms to Hash-Evasion and Hash-Inversion Attacks
Jordan Madden, Moxanki Bhavsar, Lhamo Dorje, Xiaohua Li
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Unveiling Synthetic Faces: How Synthetic Datasets Can Expose Real Identities
Hatef Otroshi Shahreza, Sébastien Marcel
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulations
Lukas Struppek, Dominik Hintersdorf, Felix Friedrich, Manuel Brack, Patrick Schramowski, Kristian Kersting
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone
Moral Persuasion in Large Language Models: Evaluating Susceptibility and Ethical Alignment
Allison Huang, Carlos Mougan, Yulu Pi
- Published: 15 Oct 2024, Last Modified: 29 Dec 2024
- AdvML-Frontiers 2024
- Readers: Everyone