33 citations · 49 across the 42 of their papers we have counts for
45 papers
AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes
Xun Wang, Bihe Zhao, Michael Backes +2
Commercial LLM APIs advertise a specific foundation model, but the served backbone may be silently substituted, quantized, or wrapped, for example to save deployment costs. All exi…
TabPATE: Differentially Private Tabular In-Context Learning Without Public Data
Dariush Wahdany, Matthew Jagielski, Jesse C. Cresswell +2
Tabular foundation models enable accurate in-context learning (ICL) from small labeled datasets, but the private records placed in context can leak through model predictions. We fi…
Dataset Usage Inference without Shadow Models or Held-out Data
Wojciech Łapacz, Stanisław Pawlak, Jan Dubiński +2
How much of my data was used to train a machine learning model? Dataset Usage Inference (DUI) aims to answer this by estimating what fraction of a dataset contributed to a model's…
Concept Removal for Frontier Image Generative Models
Aditya Kumar, Pierre Joly, Adam Dziedzic +1
Image generative models are trained on massive, largely uncurated internet-scale datasets that contain undesirable visual concepts. Efficiently removing such concepts from the mode…
Natural Identifiers for Privacy and Data Audits in Large Language Models
Lorenzo Rossi, Bartłomiej Marek, Franziska Boenisch +1
Assessing the privacy of large language models (LLMs) presents significant challenges. In particular, most existing methods for auditing differential privacy require the insertion…
MultiMem: Measuring and Mitigating Memorization in Multi-Modal Contrastive Learning
Wenhao Wang, Franziska Boenisch, Michael Backes +1
Memorization in machine learning models enables high performance on rare in-distribution samples by capturing their atypical patterns. However, it also causes harmful retention of…
Data Provenance for Image Auto-Regressive Generation
Bihe Zhao, Louis Kerner, Michel Meintz +3
Image autoregressive models (IARs) have recently demonstrated remarkable capabilities in visual content generation, achieving photorealistic quality and rapid synthesis through the…
MGI: Member vs Generated Inference
Bihe Zhao, Michel Meintz, Juangui Xu +2
As generative models increasingly produce samples that are indistinguishable from human-created content, it becomes difficult to determine whether a given data point was part of a…
Benchmarking Empirical Privacy Protection for Adaptations of Large Language Models
Bartłomiej Marek, Lorenzo Rossi, Vincent Hanke +4
Recent work has applied differential privacy (DP) to adapt large language models (LLMs) for sensitive applications, offering theoretical guarantees. However, its practical effectiv…
SERUM: Simple, Efficient, Robust, and Unifying Marking for Diffusion-based Image Generation
Jan Kociszewski, Hubert Jastrzębski, Tymoteusz Stępkowski +4
We propose SERUM: an intriguingly simple yet highly effective method for marking images generated by diffusion models (DMs). We only add a unique watermark noise to the initial dif…
Conditioned Activation Transport for T2I Safety Steering
Maciej Chrabąszcz, Aleksander Szymczyk, Jan Dubiński +3
Despite their impressive capabilities, current Text-to-Image (T2I) models remain prone to generating unsafe and toxic content. While activation steering offers a promising inferenc…
Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning
Dariush Wahdany, Matthew Jagielski, Adam Dziedzic +1
In machine learning, curation is used to select the most valuable data for improving both model accuracy and computational efficiency. Recently, curation has also been explored as…
On Stealing Graph Neural Network Models
Marcin Podhajski, Jan Dubiński, Franziska Boenisch +3
Current graph neural network (GNN) model-stealing methods rely heavily on queries to the victim model, assuming no hard query limits. However, in reality, the number of allowed que…
Memorization in Graph Neural Networks
Adarsh Jamadandi, Jing Xu, Adam Dziedzic +1
Deep neural networks (DNNs) have been shown to memorize their training data, yet similar analyses for graph neural networks (GNNs) remain largely under-explored. We introduce NCMem…
Localizing and Mitigating Memorization in Image Autoregressive Models
Aditya Kasliwal, Franziska Boenisch, Adam Dziedzic
Image AutoRegressive (IAR) models have achieved state-of-the-art performance in speed and quality of generated images. However, they also raise concerns about memorization of their…
Demystifying Foreground-Background Memorization in Diffusion Models
Jimmy Z. Di, Yiwei Lu, Yaoliang Yu +3
Diffusion models (DMs) memorize training images and can reproduce near-duplicates during generation. Current detection methods identify verbatim memorization but fail to capture tw…
Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs)
Iyiola E. Olatunji, Franziska Boenisch, Jing Xu +1
Large Language Models (LLMs) are increasingly integrated with graph-structured data for tasks like node classification, a domain traditionally dominated by Graph Neural Networks (G…
Implementing Adaptations for Vision AutoRegressive Model
Kaif Shaikh, Franziska Boenisch, Adam Dziedzic
Vision AutoRegressive model (VAR) was recently introduced as an alternative to Diffusion Models (DMs) in image generation domain. In this work we focus on its adaptations, which ai…
Finding DoRI: Discovery of Retained Images in Diffusion Models
Antoni Kowalczuk, Dominik Hintersdorf, Lukas Struppek +3
Text-to-image diffusion models (DMs) have achieved remarkable success in image generation. However, concerns about data privacy and intellectual property remain due to their potent…
Radioactive Watermarks in Diffusion and Autoregressive Image Generative Models
Michel Meintz, Jan Dubiński, Franziska Boenisch +1
Image generative models have become increasingly popular, but training them requires large datasets that are costly to collect and curate. To circumvent these costs, some parties m…
Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs
Xun Wang, Jing Xu, Franziska Boenisch +3
Prompting has become a dominant paradigm for adapting large language models (LLMs). While discrete (textual) prompts are widely used for their interpretability, soft (parameter) pr…
Unlocking Post-hoc Dataset Inference with Synthetic Data
Bihe Zhao, Pratyush Maini, Franziska Boenisch +1
The remarkable capabilities of Large Language Models (LLMs) can be mainly attributed to their massive training datasets, which are often scraped from the internet without respectin…
BitMark: Watermarking Bitwise Autoregressive Image Generative Models
Louis Kerner, Michel Meintz, Bihe Zhao +2
State-of-the-art text-to-image models generate photorealistic images at an unprecedented speed. This work focuses on models that operate in a bitwise autoregressive manner over a d…
Exploring the limits of strong membership inference attacks on large language models
Jamie Hayes, Ilia Shumailov, Christopher A. Choquette-Choo +13
State-of-the-art membership inference attacks (MIAs) typically require training many reference models, making it difficult to scale these attacks to large pre-trained language mode…