Generative diffusion models, including Stable Diffusion and Midjourney, can generate visually appealing, diverse, and high-resolution images for various applications. These models are trained on billions of internet-sourced images, raising significant concerns about the potential unauthorized use of copyright-protected images. In this paper, we examine whether it is possible to determine if a specific image was used in the training set, a problem known in the cybersecurity community as a membership inference attack. Our focus is on Stable Diffusion, and we address the challenge of designing a fair evaluation framework to answer this membership question. We propose a new dataset to establish a fair evaluation setup and apply it to Stable Diffusion, also applicable to other generative models. With the proposed dataset, we execute membership attacks (both known and newly introduced). Our research reveals that previously proposed evaluation setups do not provide a full understanding of the effectiveness of membership inference attacks. We conclude that the membership inference attack remains a significant challenge for large diffusion models (often deployed as black-box systems), indicating that related privacy and copyright issues will persist in the foreseeable future.

Understanding the attributes of critical data and implementing suitable security measures help organisations bolster their data-protection strategies and diminish the potential impacts of ransomware incidents. Unauthorised extraction and acquisition of data are the principal objectives of most cyber invasions. We underscore the severity of this issue using a recent attack by the Clop ransomware group, which exploited the MOVEit Transfer vulnerability and bypassed network-detection mechanisms to exfiltrate data via a Command and Control server. As a countermeasure, we propose a method called Buffer-Based Signature Verification (BBSV). This approach involves embedding 32-byte tags into files prior to their storage in the cloud, thus offering enhanced data protection. The BBSV method can be integrated into software like MOVEit Secure Managed File Transfer, thereby thwarting attempts by ransomware to exfiltrate data. Empirically tested using a BBSV prototype, our approach was able to successfully halt the encryption process for 80 ransomware instances from 70 ransomware families. BBSV not only stops the encryption but also prevents data exfiltration when data are moved or written from the original location by adversaries. We further develop a hypothetical exploit scenario in which an adversary manages to bypass the BBSV, illicitly transmits data to a Command and Control server, and then removes files from the original location. We construct an extended state space, in which each state represents a tuple that integrates user authentication and system components at the filesystem level.

Neural networks trained on data whose distribution is shifted in time suffer greatly from performance degradation.This problem is known as catastrophic forgetting, i.e. learning new classes leads to loss of accuracy on previously seen ones.A replay buffer can mitigate this problem by storing and reusing some of the data.In this paper, we propose a modification of sampling to the memory buffer using deep features extracted from the classifier itself to increase the diversity of stored samples.Our method demonstrates a consistent reduction in forgetting verified on different settings for MNIST, SVHN and CIFAR-10 datasets.91

We introduce a new training paradigm that enforces interval constraints on neural network parameter space to control forgetting. Contemporary Continual Learning (CL) methods focus on training neural networks efficiently from a stream of data, while reducing the negative impact of catastrophic forgetting, yet they do not provide any firm guarantees that network performance will not deteriorate uncontrollably over time. In this work, we show how to put bounds on forgetting by reformulating continual learning of a model as a continual contraction of its parameter space. To that end, we propose Hyperrectangle Training, a new training methodology where each task is represented by a hyperrectangle in the parameter space, fully contained in the hyperrectangles of the previous tasks. This formulation reduces the NP-hard CL problem back to polynomial time while providing full resilience against forgetting. We validate our claim by developing InterContiNet (Interval Continual Learning) algorithm which leverages interval arithmetic to effectively model parameter regions as hyperrectangles. Through experimental results, we show that our approach performs well in a continual learning setup without storing data from previous tasks.

This paper presents a mechanism for detecting adversarial examples based on data representations taken from the hidden layers of the target network. Individual autoencoders at intermediate layers of the target network are trained for this purpose. This describes the manifold of true data and, in consequence, can be used to classify whether a given example has the same characteristics as true data. It also gives insight into the behavior of adversarial examples and their flow through the layers of a deep neural network. Experimental results show that our method outperforms the state of the art in supervised and unsupervised settings.

Compression is widely used in Internet applications to save communication time, bandwidth and storage. Recently invented by Jarek Duda asymmetric numeral system (ANS) offers an improved efficiency and a close to optimal compression. The ANS algorithm has been deployed by major IT companies such as Facebook, Google and Apple. Compression by itself does not provide any security (such as confidentiality or authentication of transmitted data). An obvious solution to this problem is an encryption of compressed bitstream. However, it requires two algorithms: one for compression and the other for encryption. In this work, we investigate natural properties of ANS that allow to incorporate authenticated encryption using as little cryptography as possible. We target low-level security communication and storage such as transmission of data from IoT devices/sensors. In particular, we propose three solutions for joint compression and encryption (compcrypt). The solutions offer different tradeoffs between security and efficiency assuming a slight compression deterioration. All of them use a pseudorandom bit generator (PRBG) based on lightweight stream ciphers. The first solution is close to original ANS and applies state jumps controlled by PRBG. The second one employs two copies of ANS, where compression is switched between the copies. The switch is controlled by a PRBG bit. The third compcrypt modifies the encoding function of ANS depending on PRBG bits. Security and efficiency of the proposed compcrypt algorithms are evaluated. The first compcrypt is the most efficient with a slight loss of compression quality. The second one consumes more storage but the loss of compression quality is negligible. The last compcrypt offers the best security but is the least efficient.

In this paper, we investigate Keccak — the cryptographic hash function adopted as the SHA-3 standard. We propose a malicious variant of the function, where new round constants are introduced. We show that for such a variant, collision and preimage attacks are possible. We also identify a class of w eak keys for malicious Keccak working in the MAC mode. Ideas presented in the paper were verified by implementing the attacks on the function with the 128-bit hash. Additionally, we show how the idea of malicious Keccak could be used in differential fault analysis against real Keccak working in the keyed mode such as the authenticated encryption mode.

We investigate six authenticated encryption schemes (ACORN, ASCON-128a, ICEPOLE-128a, Ketje Jr, MORUS, and NORX-32) from the CAESAR competition. We aim at state recovery attacks using a SAT solver as a main tool. Our analysis reveals that these schemes, as submitted to CAESAR, provide strong resistance against SAT-based state recoveries. To shed a light on their security margins, we also analyse modified versions of these algorithms, including round-reduced variants and versions with higher security claims. Our attacks on such variants require only a few known plaintext-ciphertext pairs and small memory requirements (to run the SAT solver), whereas time complexity varies from very practical (few seconds on a desktop PC) to 'theoretical' attacks.

In this paper we investigate the security margin of MORUS-an authenticated cipher taking part in the CAESAR competition. We propose a new key recovery approach, which can be seen as an accelerated exhaustive search. We also verify the resistance of MORUS against internal differential and rotational cryptanalysis. Our analysis reveals that the cipher has a solid security margin and a lack of round constants does not bring any weakness. Our work helps to reliably evaluate this new, high-performance algorithm, which is particularly important in the context of the ongoing CAESAR competition.

In this work we focus on the tweakable block cipher Scream, We have analysed Scream with the techniques, which previously have not been applied to this algorithm, that is differential-linear and impossible differential cryptanalysis. This is work in progress towards a comprehensive evaluation of Scream. We think it is essential to analyse these new, promising algorithms with a possibly wide range of cryptanalytic tools and techniques. Our work helps to realize this goal.

The PRINCE cipher is the result of a cooperation between the Technical University of Denmark, NXP Semiconductors and the Ruhr University Bochum. The cipher was designed to reach an extremely low‐latency encryption and instant response time. PRINCE has already gained a lot of attention from the academic community, however, most of the attacks are theoretical, usually with very high time or data complexity. This work helps to fill the gap in more practically oriented attacks, with more realistic scenarios and complexities. New attacks are presented, up to seven rounds, relying on integral and higher‐order differential cryptanalysis.

In recent years the functional decomposition has found an application in many fields of modern engineering and science, such as combinational and sequential logic synthesis for VLSI systems, pattern analysis, knowledge discovery, machine learning, decision systems, data bases, data mining etc. However, the lack of an effective and efficient method of the input variable partitioning limits its practical usefulness in complex systems. A classical method based on a systematic search of the whole solution space is inefficient due to its nonpolynomial time complexity. In this paper, a heuristic method for the input variable partitioning is proposed and discussed. The method is based on the application of evolutionary algorithms that allows exploring the possible solution space of a problem while keeping the high-quality solutions in this reduced space. The experimental results show that the proposed heuristic method is able to construct an optimal or near optimal solution very efficiently even for large systems. It is much faster than the systematic method while delivering results of comparable quality.