Related papers: FBI: Fingerprinting models with Benign Inputs

Model-serving systems have become increasingly popular, especially in real-time web applications. In such systems, users send queries to the server and specify the desired performance metrics (e.g., desired accuracy, latency). The server…

In spite of intense research efforts, deep neural networks remain vulnerable to adversarial examples: an input that forces the network to confidently produce incorrect outputs. Adversarial examples are typically generated by an attack…

Generating realistic biometric images has been an interesting and, at the same time, challenging problem. Classical statistical models fail to generate realistic-looking fingerprint images, as they are not powerful enough to capture the…

Deep learning-based models have been very successful in achieving state-of-the-art results in many of the computer vision, speech recognition, and natural language processing tasks in the last few years. These models seem a natural fit for…

Many deployed learned models are black boxes: given input, returns output. Internal information about the model, such as the architecture, optimisation procedure, or training data, is not disclosed explicitly as it might contain proprietary…

Large language models (LLMs) are often modified after release through post-processing such as post-training or quantization, which makes it challenging to determine whether one model is derived from another. Existing provenance detection…

Face forgery generation technologies generate vivid faces, which have raised public concerns about security and privacy. Many intelligent systems, such as electronic payment and identity verification, rely on face forgery detection.…

The rapid growth of large language models raises pressing concerns about intellectual property protection under black-box deployment. Existing backdoor-based fingerprints either rely on rare tokens -- leading to high-perplexity inputs…

Federated Learning (FL) is increasingly adopted as a decentralized machine learning paradigm due to its capability to preserve data privacy by training models without centralizing user data. However, FL is susceptible to indirect privacy…

The behavior of LLMs does not depend solely on the model itself. Components of the inference system, such as the inference engine, attention backend, and hardware platform, subtly influence how inputs are processed. These components differ…

Deep neural networks have demonstrated promising performance on image recognition tasks. However, they may heavily rely on confounding factors, using irrelevant artifacts or bias within the dataset as the cue to improve performance. When a…

Over the past years, deep generative models have achieved a new level of performance. Generated data has become difficult, if not impossible, to be distinguished from real data. While there are plenty of use cases that benefit from this…

In the recent past, different researchers have proposed privacy-enhancing face recognition systems designed to conceal soft-biometric attributes at feature level. These works have reported impressive results, but generally did not consider…

Backdoor attacks pose a significant security vulnerability for deep neural networks (DNNs), enabling them to operate normally on clean inputs but manipulate predictions when specific trigger patterns occur. Currently, post-training backdoor…

Fingerprint classification is one of the most common approaches to accelerate the identification in large databases of fingerprints. Fingerprints are grouped into disjoint classes, so that an input fingerprint is compared only with those…

The recent proliferation of photorealistic images created by generative models has sparked both excitement and concern, as these images are increasingly indistinguishable from real ones to the human eye. While offering new creative and…

Text-to-image models are commercially valuable assets often distributed under restrictive licenses, but such licenses are enforceable only when violations can be detected. Existing methods require pre-deployment watermarking or internal…

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…

Data-trained predictive models see widespread use, but for the most part they are used as black boxes which output a prediction or score. It is therefore hard to acquire a deeper understanding of model behavior, and in particular how…

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed…