Nader Sehatbakhsh

Hossein Khalili, Seongbin Park, Vincent Li et al. · gatech

Autonomous mobile systems increasingly rely on deep neural networks for perception and decision-making. While effective, these systems are vulnerable to adversarial machine learning attacks where minor input perturbations can significantly impact outcomes. Common countermeasures involve adversarial training and/or data or network transformation. These methods, though effective, require full access to typically proprietary classifiers and are costly for large models. Recent solutions propose purification models, which add a "purification" layer before classification, eliminating the need to modify the classifier directly. Despite their effectiveness, these methods are compute-intensive, making them unsuitable for mobile systems where resources are limited and low latency is essential. This paper introduces LightPure, a new method that enhances adversarial image purification. It improves the accuracy of existing purification methods and provides notable enhancements in speed and computational efficiency, making it suitable for mobile devices with limited resources. Our approach uses a two-step diffusion and one-shot Generative Adversarial Network (GAN) framework, prioritizing latency without compromising robustness. We propose several new techniques to achieve a reasonable balance between classification accuracy and adversarial robustness while maintaining desired latency. We design and implement a proof-of-concept on a Jetson Nano board and evaluate our method using various attack scenarios and datasets. Our results show that LightPure can outperform existing methods by up to 10x in terms of latency while achieving higher accuracy and robustness for various attack scenarios. This method offers a scalable and effective solution for real-world mobile systems.

Alexander Vilesov, Yuan Tian, Nader Sehatbakhsh et al. · gatech

The exponential progress in generative AI poses serious implications for the credibility of all real images and videos. There will exist a point in the future where 1) digital content produced by generative AI will be indistinguishable from those created by cameras, 2) high-quality generative algorithms will be accessible to anyone, and 3) the ratio of all synthetic to real images will be large. It is imperative to establish methods that can separate real data from synthetic data with high confidence. We define real images as those that were produced by the camera hardware, capturing a real-world scene. Any synthetic generation of an image or alteration of a real image through generative AI or computer graphics techniques is labeled as a synthetic image. To this end, this document aims to: present known strategies in detection and cryptography that can be employed to verify which images are real, weight the strengths and weaknesses of these strategies, and suggest additional improvements to alleviate shortcomings.

Sayedeh Leila Noorbakhsh, Hossein Khalili, Nader Sehatbakhsh · gatech

Collaborative edge-cloud inference enables resource-constrained devices to leverage large language models (LLMs) by offloading partial computation to cloud servers. However, transmitting intermediate activations exposes sensitive user prompts to prompt inversion attacks, where an adversary reconstructs the original input from shared representations. Existing defenses rely largely on heuristic perturbations or empirical tuning, offering limited theoretical understanding of privacy leakage and its interaction with utility and latency constraints. We propose an information-theoretic defense framework for prompt inversion in collaborative LLM inference. Our approach learns privacy-preserving representations by explicitly minimizing the mutual information between intermediate activations and the input prompt while maintaining task utility under computational constraints. We derive theoretical guarantees on prompt reconstruction error, characterize fundamental privacy-utility tradeoffs, and establish token-level accuracy bounds for downstream inference. We then propose a novel defense based on privacy adapters implemented via low-dimensional information bottlenecks. Extensive experiments across multiple settings demonstrate that our method achieves superior privacy-utility-latency tradeoffs compared to existing defenses (up to 35% reduction in attack success), providing a principled foundation for private and efficient collaborative LLM inference.

Robert Chang, Logan Kuo, Arthur Liu et al.

As the use of Voice Processing Systems (VPS) continues to become more prevalent in our daily lives through the increased reliance on applications such as commercial voice recognition devices as well as major text-to-speech software, the attacks on these systems are increasingly complex, varied, and constantly evolving. With the use cases for VPS rapidly growing into new spaces and purposes, the potential consequences regarding privacy are increasingly more dangerous. In addition, the growing number and increased practicality of over-the-air attacks have made system failures much more probable. In this paper, we will identify and classify an arrangement of unique attacks on voice processing systems. Over the years research has been moving from specialized, untargeted attacks that result in the malfunction of systems and the denial of services to more general, targeted attacks that can force an outcome controlled by an adversary. The current and most frequently used machine learning systems and deep neural networks, which are at the core of modern voice processing systems, were built with a focus on performance and scalability rather than security. Therefore, it is critical for us to reassess the developing voice processing landscape and to identify the state of current attacks and defenses so that we may suggest future developments and theoretical improvements.

Nader Sehatbakhsh, Ellie Daw, Onur Savas et al.

As machine learning becomes a more mainstream technology, the objective for governments and public sectors is to harness the power of machine learning to advance their mission by revolutionizing public services. Motivational government use cases require special considerations for implementation given the significance of the services they provide. Not only will these applications be deployed in a potentially hostile environment that necessitates protective mechanisms, but they are also subject to government transparency and accountability initiatives which further complicates such protections. In this paper, we describe how the inevitable interactions between a user of unknown trustworthiness and the machine learning models, deployed in governments and public sectors, can jeopardize the system in two major ways: by compromising the integrity or by violating the privacy. We then briefly overview the possible attacks and defense scenarios, and finally, propose recommendations and guidelines that once considered can enhance the security and privacy of the provided services.