22 citations · 67 across the 35 of their papers we have counts for
13 papers · 1 filter
The Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMs
Toluwani Aremu, Manit Baser, Mohan Gurusamy +2
Open-weight language models can be downloaded, modified, and deployed beyond their developers' control, limiting the effectiveness of centrally enforced safeguards. Recent work has…
Context Inference Attacks Without Jailbreaks
Prince Jha, Samuele Poppi, Nils Lukas
Agentic AI systems are increasingly deployed to process sensitive data at inference time, such as healthcare records or financial documents assembled into a hidden \emph{context} b…
Watermarking Should Be Treated as a Monitoring Primitive
Toluwani Aremu, Nils Lukas, Jie Zhang
Watermarking is widely proposed for provenance, attribution, and safety monitoring in generative models. We argue that it should be evaluated and governed as a monitoring primitive…
Adaptively Robust LLM Monitoring via Activation Watermarking
Toluwani Aremu, Daniil Ognev, Samuele Poppi +1
Providers monitor deployed large language models (LLMs) to detect misuse that they cannot prevent. LLM monitoring is deterministic and often openly available, so …
SPQR: A Multi-Dimensional Benchmark for Safety Alignment under Benign Model Adaptation
Mohammed Talha Alam, Nada Saadi, Fahad Shamshad +4
Text-to-image diffusion models can emit copyrighted, unsafe, or private content. Safety alignment aims to suppress specific concepts, yet evaluations seldom test whether safety per…
BURN: Backdoor Unlearning via Adversarial Boundary Analysis
Yanghao Su, Jie Zhang, Yiming Li +6
Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering…
Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
Toluwani Aremu, Noor Hussein, Munachiso Nwadike +5
Watermarking enables GenAI providers to verify whether content was generated by their models. A watermark is a hidden signal in the content, whose presence can be detected using a…
Optimizing Adaptive Attacks against Watermarks for Language Models
Abdulrahman Diaa, Toluwani Aremu, Nils Lukas
Large Language Models (LLMs) can be misused to spread unwanted content at scale. Content watermarking deters misuse by hiding messages in content, enabling its detection using a se…
PEPSI: Practically Efficient Private Set Intersection in the Unbalanced Setting
Rasoul Akhavan Mahdavi, Nils Lukas, Faezeh Ebrahimianghazani +7
Two parties with private data sets can find shared elements using a Private Set Intersection (PSI) protocol without revealing any information beyond the intersection. Circuit PSI p…
Leveraging Optimization for Adaptive Attacks on Image Watermarks
Nils Lukas, Abdulrahman Diaa, Lucas Fenaux +1
Untrustworthy users can misuse image generators to synthesize high-quality deepfakes and engage in unethical activities. Watermarking deters misuse by marking generated content wit…
Pick your Poison: Undetectability versus Robustness in Data Poisoning Attacks
Nils Lukas, Florian Kerschbaum
Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samp…
Fast and Private Inference of Deep Neural Networks by Co-designing Activation Functions
Abdulrahman Diaa, Lucas Fenaux, Thomas Humphries +9
Machine Learning as a Service (MLaaS) is an increasingly popular design where a company with abundant computing resources trains a deep neural network and offers query access for t…
SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)
Nils Lukas, Edward Jiang, Xinda Li +1
Deep Neural Network (DNN) watermarking is a method for provenance verification of DNN models. Watermarking should be robust against watermark removal attacks that derive a surrogat…