Satire, a form of artistic expression combining humor with implicit critique, holds significant social value by illuminating societal issues. Despite its cultural and societal significance, satire comprehension, particularly in purely visual forms, remains a challenging task for current vision-language models. This task requires not only detecting satire but also deciphering its nuanced meaning and identifying the implicated entities. Existing models often fail to effectively integrate local entity relationships with global context, leading to misinterpretation, comprehension biases, and hallucinations. To address these limitations, we propose SatireDecoder, a training-free framework designed to enhance satirical image comprehension. Our approach proposes a multi-agent system performing visual cascaded decoupling to decompose images into fine-grained local and global semantic representations. In addition, we introduce a chain-of-thought reasoning strategy guided by uncertainty analysis, which breaks down the complex satire comprehension process into sequential subtasks with minimized uncertainty. Our method significantly improves interpretive accuracy while reducing hallucinations. Experimental results validate that SatireDecoder outperforms existing baselines in comprehending visual satire, offering a promising direction for vision-language reasoning in nuanced, high-level semantic tasks.

With the widespread use of virtual reality applications, 3D scene generation has become a new challenging research frontier. 3D scenes have highly complex structures and need to ensure that the output is dense, coherent, and contains all necessary structures. Many current 3D scene generation methods rely on pre-trained text-to-image diffusion models and monocular depth estimators. However, the generated scenes occupy large amounts of storage space and often lack effective regularisation methods, leading to geometric distortions. To this end, we propose BloomScene, a lightweight structured 3D Gaussian splatting for crossmodal scene generation, which creates diverse and high-quality 3D scenes from text or image inputs. Specifically, a crossmodal progressive scene generation framework is proposed to generate coherent scenes utilizing incremental point cloud reconstruction and 3D Gaussian splatting. Additionally, we propose a hierarchical depth prior-based regularization mechanism that utilizes multi-level constraints on depth accuracy and smoothness to enhance the realism and continuity of the generated scenes. Ultimately, we propose a structured context-guided compression mechanism that exploits structured hash grids to model the context of unorganized anchor attributes, which significantly eliminates structural redundancy and reduces storage overhead. Comprehensive experiments across multiple scenes demonstrate the significant potential and advantages of our framework compared with several baselines.

Diffusion models have shown excellent performance in text-to-image generation. Nevertheless, existing methods often suffer from performance bottlenecks when handling complex prompts that involve multiple objects, characteristics, and relations. Therefore, we propose a Multi-agent Collaboration-based Compositional Diffusion (MCCD) for text-to-image generation for complex scenes. Specifically, we design a multi-agent collaboration-based scene parsing module that generates an agent system comprising multiple agents with distinct tasks, utilizing MLLMs to extract various scene elements effectively. In addition, Hierarchical Compositional diffusion utilizes a Gaussian mask and filtering to refine bounding box regions and enhance objects through region enhancement, resulting in the accurate and high-fidelity generation of complex scenes. Comprehensive experiments demonstrate that our MCCD significantly improves the performance of the baseline models in a training-free manner, providing a substantial advantage in complex scene generation.

Neural network (NN) models implemented in embedded devices have been shown to be susceptible to side-channel attacks (SCAs), allowing recovery of proprietary model parameters, such as weights and biases. There are already available countermeasure methods currently used for protecting cryptographic implementations that can be tailored to protect embedded NN models. Shuffling, a hiding-based countermeasure that randomly shuffles the order of computations, was shown to be vulnerable to SCA when the Fisher-Yates algorithm is used. In this article, we propose a design of an SCA-secure version of the Fisher-Yates algorithm. By integrating the masking technique for modular reduction and Blakely’s method for modular multiplication, we effectively remove the vulnerability in the division operation that led to side-channel leakage in the original version of the algorithm. We experimentally evaluate that the countermeasure is effective against SCA by implementing a correlation power analysis (CPA) attack on an embedded NN model implemented on ARM Cortex-M4. Compared to the original proposal, the memory overhead is$2\times $the biggest layer of the network, while the time overhead varies from 4% to 0.49% for a layer with 100 and 1000 neurons, respectively.

Multimodal Sentiment Analysis (MSA) is an important research area that aims to understand and recognize human sentiment through multiple modalities. The complementary information provided by multimodal fusion promotes better sentiment analysis compared to utilizing only a single modality. Nevertheless, in real-world applications, many unavoidable factors may lead to situations of uncertain modality missing, thus hindering the effectiveness of multimodal modeling and degrading the model’s performance. To this end, we propose a Hierarchical Representation Learning Framework (HRLF) for the MSA task under uncertain missing modalities. Specifically, we propose a fine-grained representation factorization module that sufficiently extracts valuable sentiment information by factorizing modality into sentiment-relevant and modality-specific representations through crossmodal translation and sentiment semantic reconstruction. Moreover, a hierarchical mutual information maximization mechanism is introduced to incrementally maximize the mutual information between multi-scale representations to align and reconstruct the high-level semantics in the representations. Ultimately, we propose a hierarchical adversarial learning mechanism that further aligns and adapts the latent distribution of sentiment-relevant representations to produce robust joint multimodal representations. Comprehensive experiments on three datasets demonstrate that HRLF significantly improves MSA performance under uncertain modality missing cases.

The idea of balancing the side-channel leakage in software was proposed more than a decade ago. Just like with other hiding-based countermeasures, the goal is not to hide the leakage completely but to significantly increase the effort required for the attack. Previous approaches focused on two directions: either balancing the Hamming weight of the processed data or deriving the code by using stochastic leakage profiling. In this brief, we build upon these results by proposing a novel approach that combines the two directions. We provide the theory behind our encoding scheme backed by experimental results on a 32-bit ARM Cortex-M4 microcontroller. Our results show that such a combination gives better side-channel resistance properties than each of the two methods separately.

Neural network implementations are known to be vulnerable to physical attack vectors such as fault injection attacks. As of now, these attacks were only utilized during the inference phase. In this work, we explore a novel attack paradigm by injecting faults during the training phase in a way that the resulting network can be attacked during deployment without the necessity of further faulting. We discuss attacks against ReLU activation functions that make it possible to generate a family of malicious inputs, which are called fooling inputs, to be used at inference time to induce controlled misclassifications. Such malicious inputs are obtained by mathematically solving a system of linear equations that would cause a particular behaviour on the attacked activation functions, similar to the one induced in training through faulting. We call such attacks fooling backdoors as the faults at training phase inject backdoors into the network that allow an attacker to produce fooling inputs. We evaluate our approach against multi-layer perceptron networks and convolutional networks on a popular image classification task obtaining high attack success rates (60% - 100%) and high classification confidence when as little as 25 neurons are attacked while preserving high accuracy on the original classification task.

Side-channel and fault injection attacks are well-researched topics within physical security of cryptographic implementations. They can reduce the complexity of the key retrieval to trivial numbers. It was shown that their combination is even more effective, for example in breaking redundancy countermeasures. In this paper, we present the first semi-blind combined attack that allows secret key retrieval in unknown plaintext and ciphertext scenario. SBCMA – Semi-Blind Combined Middle-round Attack is aimed at bit-permutation ciphers, such as GIFT-128 which serves as a case study for this work. On average, it can recover GIFT-128 master key with 92.17 encryptions and 91.17 faults. For GIFT-128 based NIST LWC Round 2 candidates, SBCMA requires 13.79 sessions and 94.32 faults on average.

Proximity attacks allow an adversary to uncover the location of a victim by repeatedly issuing queries with fake location data. These attacks have been mostly studied in scenarios where victims remain static and there are no constraints that limit the actions of the attacker. In such a setting, it is not difficult for the attacker to locate a particular victim and quantifying the effort for doing so is straightforward. However, it is far more realistic to consider scenarios where potential victims present a particular mobility pattern. In this article, we consider abstract (constrained and unconstrained) attacks on services that provide location information on other users in the proximity. We derive strategies for constrained and unconstrained attackers, and show that when unconstrained they can practically achieve success with theoretically optimal effort. We then propose a simple yet effective constraint that may be employed by a proximity service (for example, running in the cloud or using a suitable two-party protocol) as a countermeasure to increase the effort for the attacker several orders of magnitude both in simulated and real-world cases.

Neural networks have been shown to be vulnerable against fault injection attacks. These attacks change the physical behavior of the device during the computation, resulting in a change of value that is currently being computed. They can be realized by various techniques, ranging from clock/voltage glitching to application of lasers to rowhammer. Previous works have mostly explored fault attacks for output misclassification, thus affecting the reliability of neural networks. In this article, we investigate the possibility to reverse engineer neural networks with fault attacks. Sign bit flip fault attack enables the reverse engineering by changing the sign of intermediate values. We develop the first exact extraction method on deep-layer feature extractor networks that provably allows the recovery of proprietary model parameters. Our experiments with Keras library show that the precision error for the parameter recovery for the tested networks is less than$10^{-13}$with the usage of 64-bit floats, which improves the current state of the art by six orders of magnitude.

Physical security of NIST lightweight cryptography competition candidates is gaining importance as the standardization process progresses. Side-channel attacks (SCA) are a well-researched topic within the physical security of cryptographic implementations. It was shown that collisions in the intermediate values can be captured by side-channel measurements to reduce the complexity of the key retrieval to trivial numbers. In this paper, we target a specific bit permutation vulnerability in the block cipher GIFT that allows the attacker to mount a key recovery attack. We present a novel SCA methodology called DCSCA - Differential Ciphertext SCA, which follows principles of differential fault analysis, but instead of the usage of faults, it utilizes SCA and statistical distribution of intermediate values. We simulate the attack on a publicly available bitslice implementation of GIFT, showing the practicality of the attack. We further show the application of the attack on GIFT-based AEAD schemes (GIFT-COFB, ESTATE, HYENA, and SUNDAE-GIFT) proposed for the NIST LWC competition. DCSCA can recover the master key with 213.39AEAD sessions, assuming 32 encryptions per session.

Cryptographic implementations are often vulnerable against physical attacks, fault injection analysis being among the most popular techniques. On par with development of attacks, the area of countermeasures is advancing rapidly, utilizing both hardware- and software-based approaches. When it comes to software encoding countermeasures for fault protection and their evaluation, there are very few proposals so far, mostly focusing on single operations rather than cipher as a whole. In this paper we propose an evaluation framework that can be used for analyzing the effectivity of software encoding countermeasures against fault attacks. We first formalize the encoding schemes in software, helping us to define what properties are required when designing a fault protection. Based on these findings, we develop an evaluation metric that can be used universally to determine the robustness of a software encoding scheme against bit flip faults and instruction skips. We provide a way to select a code according to user criteria and also a dynamic code analysis method to estimate the level of protection of assembly implementations using encoding schemes. Finally, we verify our findings by implementing a block cipher PRESENT, protected by encoding scheme based on anticodes, and provide a detailed evaluation of this implementation using different codes.

Deep learning approaches have become popular for Side-Channel Analysis (SCA) in the recent years. Especially Convolutional Neural Networks (CNN) due to their natural ability to overcome jitter-based as well as masking countermeasures. Most of the recent works have been focusing on optimising the performance on given dataset, for example finding optimal architecture and using ensemble, and bypass the need for trace pre-processing. However, trace pre-processing is a long studied topic and several proven techniques exist in the literature. There is no straightforward manner to integrate those techniques into deep learning based SCA. In this paper, we propose a generic framework which allows seamless integration of multiple, user defined pre-processing techniques into the neural network architecture. The framework is based on Multi-scale Convolutional Neural Networks ( MCNN) that were originally proposed for time series analysis. MCNN are composed of multiple branches that can apply independent transformation to input data in each branch to extract the relevant features and allowing a better generalization of the model. In terms of SCA, these transformations can be used for integration of pre-processing techniques, such as phase-only correlation, principal component analysis, alignment methods, etc. We present successful results on generic network which generalizes to different publicly available datasets. Our findings show that it is possible to design a network that can be used in a more general way to analyze side-channel leakage traces and perform well across datasets.

Lightweight block ciphers rely on simple operations to allow compact implementation. Thanks to its efficiency, bit permutation has emerged as an optimal choice for state-wise diffusion. It can be implemented by simple wiring in hardware or shifts in software. However, efficiency and security often go against each other. In this paper, we show how bit permutations introduce a side-channel vulnerability that can be exploited to extract the secret key from the cipher. Such vulnerabilities are specific to bit permutations and do not occur in other state-wise diffusion alternatives. We propose side-channel assisted differential-plaintext attack (SCADPA) which targets this vulnerability in the bit permutation operation. SCADPA is first experimentally demonstrated on PRESENT-80 on an 8-bit microcontroller, with the best case key recovery in 17 encryptions. In Addition, we adjust SCADPA to state-of-the-art bit sliced implementation from CHES'17 with experimental evaluation on a 32-bit microcontroller. The attack is then extended to latest bit-permutation-based cipher GIFT, allowing full key recovery in 36 encryptions. Application for reverse engineering of secret S-boxes in PRESENT-like proprietary ciphers is also shown.

Recently, the NIST launched a competition for lightweight cryptography and a large number of ciphers are expected to be studied and analyzed under this competition. Apart from the classical security, the candidates are desired to be analyzed against physical attacks. Differential Fault Analysis (DFA) is an invasive physical attack method for recovering key information from cipher implementations. Up to date, almost all the block ciphers have been shown to be vulnerable against DFA, while following similar attack patterns. However, so far researchers mostly focused on particular ciphers rather than cipher families, resulting in works that reuse the same idea for different ciphers. In this article, we aim at bridging this gap, by providing a generic DFA attack method targeting Substitution-Permutation Network (SPN) based families of symmetric block ciphers. We provide the overview of the state-of-the-art of the fault attacks on SPNs, followed by generalized conditions that hold on all the ciphers of this design family. We show that for any SPN, as long as the fault mask injected before a non-linear layer in the last round follows a non-uniform distribution, the key search space can always be reduced. This shows that it is not possible to design an SPN-based cipher that is completely secure against DFA, without randomization. Furthermore, we propose a novel approach to find good fault masks that can leak the key with a small number of instances. We then developed a tool, called Joint Difference Distribution Table (JDDT) for pre-computing the solutions for the fault equations, which allows us to recover the last round key with a very small number of pairs of faulty and non-faulty ciphertexts. We evaluate our methodology on various block ciphers, including PRESENT-80, PRESENT-128, GIFT-64, GIFT-128, AES-128, LED-64, LED-128, Skinny, Pride and Prince. The developed technique would allow automated DFA analysis of several candidates in the NIST competitio

As deep learning systems are widely adopted in safety- and security-critical applications, such as autonomous vehicles, banking systems, etc., malicious faults and attacks become a tremendous concern, which potentially could lead to catastrophic consequences. In this paper, we initiate the first study of leveraging physical fault injection attacks on Deep Neural Networks (DNNs), by using laser injection technique on embedded systems. In particular, our exploratory study targets four widely used activation functions in DNNs development, that are the general main building block of DNNs that creates non-linear behaviors -- ReLu, softmax, sigmoid, and tanh. Our results show that by targeting these functions, it is possible to achieve a misclassification by injecting faults into the hidden layer of the network. Such result can have practical implications for real-world applications, where faults can be introduced by simpler means (such as altering the supply voltage).

LCD (linear complimentary dual) codes are linear codes that trivially intersect their duals. We address the question of an equivalent concept for lattices. We observe basic properties of the intersection of a lattice with its dual, and consider the construction of lattices from LCD codes using Construction A. Lattices obtained from the intersection of a code with its dual via Construction A are further discussed.

The secrecy gain of a lattice is a lattice invariant used to characterize wiretap lattice codes for Gaussian channels. The secrecy gain has been classified for unimodular lattices up to dimension 23, and so far, a few sparse examples are known for l-modular lattices, with l = 2, 3. We propose some constructions of 5-modular lattices via the Construction A of lattices from linear codes, and study the secrecy gain of the resulting lattices.