LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate the LLM's intended behavior. Recent defenses based on known-answer detection (KAD) scheme have reported near-perfect performance by observing an LLM's output to classify input data as clean or contaminated. KAD attempts to repurpose the very susceptibility to prompt injection as a defensive mechanism. We formally characterize the KAD scheme and uncover a structural vulnerability that invalidates its core security premise. To exploit this fundamental vulnerability, we methodically design an adaptive attack, DataFlip. It consistently evades KAD defenses, achieving detection rates as low as $0\%$ while reliably inducing malicious behavior with a success rate of $91\%$, all without requiring white-box access to the LLM or any optimization procedures.

Binarized Neural Networks (BNNs) are a class of deep neural networks designed to utilize minimal computational resources, which drives their popularity across various applications. Recent studies highlight the potential of mapping BNN model parameters onto emerging non-volatile memory technologies, specifically using crossbar architectures, resulting in improved inference performance compared to traditional CMOS implementations. However, the common practice of protecting model parameters from theft attacks by storing them in an encrypted format and decrypting them at runtime introduces significant computational overhead, thus undermining the core principles of in-memory computing, which aim to integrate computation and storage. This paper presents a robust strategy for protecting BNN model parameters, particularly within in-memory computing frameworks. Our method utilizes a secret key derived from a physical unclonable function to transform model parameters prior to storage in the crossbar. Subsequently, the inference operations are performed on the encrypted weights, achieving a very special case of Fully Homomorphic Encryption (FHE) with minimal runtime overhead. Our analysis reveals that inference conducted without the secret key results in drastically diminished performance, with accuracy falling below 15%. These results validate the effectiveness of our protection strategy in securing BNNs within in-memory computing architectures while preserving computational efficiency.

This paper studies the problem of extracting common randomness (CR) or secret keys from correlated random sources observed by two legitimate parties, Alice and Bob, through public discussion in the presence of an eavesdropper, Eve. We propose a practical two-stage CR extraction framework. In the first stage, the variational probabilistic quantization (VPQ) step is introduced, where Alice and Bob employ probabilistic neural network (NN) encoders to map their observations into discrete, nearly uniform random variables (RVs) with high agreement probability while minimizing information leakage to Eve. This is realized through a variational learning objective combined with adversarial training. In the second stage, a secure sketch using code-offset construction reconciles the encoder outputs into identical secret keys, whose secrecy is guaranteed by the VPQ objective. As a representative application, we study physical layer key (PLK) generation. Beyond the traditional methods, which rely on the channel reciprocity principle and require two-way channel probing, thus suffering from large protocol overhead and being unsuitable in high mobility scenarios, we propose a sensing-based PLK generation method for integrated sensing and communications (ISAC) systems, where paired range-angle (RA) maps measured at Alice and Bob serve as correlated sources. The idea is verified through both end-to-end simulations and real-world software-defined radio (SDR) measurements, including scenarios where Eve has partial knowledge about Bob's position. The results demonstrate the feasibility and convincing performance of both the proposed CR extraction framework and sensing-based PLK generation method.

Face images processed by computer vision algorithms contain sensitive personal information that malicious actors can capture without consent. These privacy and security risks highlight the need for effective face anonymization methods. Current methods struggle to propose a good trade-off between a secure scheme with high-quality image generation and reversibility for later person authentication. Diffusion-based approaches produce high-quality anonymized images but lack the secret key mechanism to ensure that only authorized parties can reverse the process. In this paper, we introduce, to our knowledge, the first secure, high-quality reversible anonymization method based on a diffusion model. We propose to combine the secret key with the latent faces representation of the diffusion model. To preserve identity-irrelevant features, generation is constrained by a facial mask, maintaining high-quality images. By using a deterministic forward and backward diffusion process, our approach enforces that the original face can be recovered with the correct secret key. We also show that the proposed method produces anonymized faces that are less visually similar to the original faces, compared to other previous work.

In this paper we show that cryptographic backdoors in a neural network (NN) can be highly effective in two directions, namely mounting the attacks as well as in presenting the defenses as well. On the attack side, a carefully planted cryptographic backdoor enables powerful and invisible attack on the NN. Considering the defense, we present applications: first, a provably robust NN watermarking scheme; second, a protocol for guaranteeing user authentication; and third, a protocol for tracking unauthorized sharing of the NN intellectual property (IP). From a broader theoretical perspective, borrowing the ideas from Goldwasser et. al. [FOCS 2022], our main contribution is to show that all these instantiated practical protocol implementations are provably robust. The protocols for watermarking, authentication and IP tracking resist an adversary with black-box access to the NN, whereas the backdoor-enabled adversarial attack is impossible to prevent under the standard assumptions. While the theoretical tools used for our attack is mostly in line with the Goldwasser et. al. ideas, the proofs related to the defense need further studies. Finally, all these protocols are implemented on state-of-the-art NN architectures with empirical results corroborating the theoretical claims. Further, one can utilize post-quantum primitives for implementing the cryptographic backdoors, laying out foundations for quantum-era applications in machine learning (ML).

The rapid development of Large Language Models (LLMs) has intensified concerns about content traceability and potential misuse. Existing watermarking schemes for sampled text often face trade-offs between maintaining text quality and ensuring robust detection against various attacks. To address these issues, we propose a novel watermarking scheme that improves both detectability and text quality by introducing a cumulative watermark entropy threshold. Our approach is compatible with and generalizes existing sampling functions, enhancing adaptability. Experimental results across multiple LLMs show that our scheme significantly outperforms existing methods, achieving over 80\% improvements on widely-used datasets, e.g., MATH and GSM8K, while maintaining high detection accuracy.

This paper explores the risk that a large language model (LLM) trained for code generation on data mined from software repositories will generate content that discloses sensitive information included in its training data. We decompose this risk, known in the literature as ``unintended memorization,'' into two components: unintentional disclosure (where an LLM presents secrets to users without the user seeking them out) and malicious disclosure (where an LLM presents secrets to an attacker equipped with partial knowledge of the training data). We observe that while existing work mostly anticipates malicious disclosure, unintentional disclosure is also a concern. We describe methods to assess unintentional and malicious disclosure risks side-by-side across different releases of training datasets and models. We demonstrate these methods through an independent assessment of the Open Language Model (OLMo) family of models and its Dolma training datasets. Our results show, first, that changes in data source and processing are associated with substantial changes in unintended memorization risk; second, that the same set of operational changes may increase one risk while mitigating another; and, third, that the risk of disclosing sensitive information varies not only by prompt strategies or test datasets but also by the types of sensitive information. These contributions rely on data mining to enable greater privacy and security testing required for the LLM training data supply chain.

Federated learning is essential for decentralized, privacy-preserving model training in the data-driven era. Quantum-enhanced federated learning leverages quantum resources to address privacy and scalability challenges, offering security and efficiency advantages beyond classical methods. However, practical and scalable frameworks addressing privacy concerns in the quantum computing era remain undeveloped. Here, we propose a practical quantum federated learning framework on quantum networks, utilizing distributed quantum secret keys to protect local model updates and enable secure aggregation with information-theoretic security. We experimentally validate our framework on a 4-client quantum network with a scalable structure. Extensive numerical experiments on both quantum and classical datasets show that adding a quantum client significantly enhances the trained global model's ability to classify multipartite entangled and non-stabilizer quantum datasets. Simulations further demonstrate scalability to 200 clients with classical models trained on the MNIST dataset, reducing communication costs by $75\%$ through advanced model compression techniques and achieving rapid training convergence. Our work provides critical insights for building scalable, efficient, and quantum-secure machine learning systems for the coming quantum internet era.

Deep neural networks (DNNs) have achieved significant success in real-world applications. However, safeguarding their intellectual property (IP) remains extremely challenging. Existing DNN watermarking for IP protection often require modifying DNN models, which reduces model performance and limits their practicality. This paper introduces FreeMark, a novel DNN watermarking framework that leverages cryptographic principles without altering the original host DNN model, thereby avoiding any reduction in model performance. Unlike traditional DNN watermarking methods, FreeMark innovatively generates secret keys from a pre-generated watermark vector and the host model using gradient descent. These secret keys, used to extract watermark from the model's activation values, are securely stored with a trusted third party, enabling reliable watermark extraction from suspect models. Extensive experiments demonstrate that FreeMark effectively resists various watermark removal attacks while maintaining high watermark capacity.

In today's digital age, the internet is essential for communication and the sharing of information, creating a critical need for sophisticated data security measures to prevent unauthorized access and exploitation. Cryptography encrypts messages into a cipher text that is incomprehensible to unauthorized readers, thus safeguarding data during its transmission. Steganography, on the other hand, originates from the Greek term for "covered writing" and involves the art of hiding data within another medium, thereby facilitating covert communication by making the message invisible. This proposed approach takes advantage of the latest advancements in Artificial Intelligence (AI) and Deep Learning (DL), especially through the application of Generative Adversarial Networks (GANs), to improve upon traditional steganographic methods. By embedding encrypted data within another medium, our method ensures that the communication remains hidden from prying eyes. The application of GANs enables a smart, secure system that utilizes the inherent sensitivity of neural networks to slight alterations in data, enhancing the protection against detection. By merging the encryption techniques of cryptography with the hiding capabilities of steganography, and augmenting these with the strengths of AI, we introduce a comprehensive security system designed to maintain both the privacy and integrity of information. This system is crafted not just to prevent unauthorized access or modification of data, but also to keep the existence of the data hidden. This fusion of technologies tackles the core challenges of data security in the current era of open digital communication, presenting an advanced solution with the potential to transform the landscape of information security.