Large language models demonstrate powerful capabilities across various natural language processing tasks, yet they also harbor safety vulnerabilities. To enhance LLM safety, various jailbreak defense methods have been proposed to guard against harmful outputs. However, improvements in model safety often come at the cost of severe over-refusal, failing to strike a good balance between safety and usability. In this paper, we first analyze the causes of over-refusal from a representation perspective, revealing that over-refusal samples reside at the boundary between benign and malicious samples. Based on this, we propose MOSR, designed to mitigate over-refusal by intervening the safety representation of LLMs. MOSR incorporates two novel components: (1) Overlap-Aware Loss Weighting, which determines the erasure weight for malicious samples by quantifying their similarity to pseudo-malicious samples in the representation space, and (2) Context-Aware Augmentation, which supplements the necessary context for rejection decisions by adding harmful prefixes before rejection responses. Experiments demonstrate that our method outperforms existing approaches in mitigating over-refusal while largely maintaining safety. Overall, we advocate that future defense methods should strike a better balance between safety and over-refusal.

Multimodal Large Language Models (MLLMs) achieve strong reasoning and perception capabilities but are increasingly vulnerable to jailbreak attacks. While existing work focuses on explicit attacks, where malicious content resides in a single modality, recent studies reveal implicit attacks, in which benign text and image inputs jointly express unsafe intent. Such joint-modal threats are difficult to detect and remain underexplored, largely due to the scarcity of high-quality implicit data. We propose ImpForge, an automated red-teaming pipeline that leverages reinforcement learning with tailored reward modules to generate diverse implicit samples across 14 domains. Building on this dataset, we further develop CrossGuard, an intent-aware safeguard providing robust and comprehensive defense against both explicit and implicit threats. Extensive experiments across safe and unsafe benchmarks, implicit and explicit attacks, and multiple out-of-domain settings demonstrate that CrossGuard significantly outperforms existing defenses, including advanced MLLMs and guardrails, achieving stronger security while maintaining high utility. This offers a balanced and practical solution for enhancing MLLM robustness against real-world multimodal threats.

--Deep Neural Networks (DNNs) are vulnerable to backdoor attacks, where attackers implant hidden triggers during training to maliciously control model behavior . T opological Evolution Dynamics (TED) has recently emerged as a powerful tool for detecting backdoor attacks in DNNs. However, TED can be vulnerable to backdoor attacks that adaptively distort topological representation distributions across network layers. T o address this limitation, we propose TED-LaST (T opological Evolution Dynamics against La undry, S low release, and T arget mapping attack strategies), a novel defense strategy that enhances TED's robustness against adaptive attacks. TED-LaST introduces two key innovations: label-supervised dynamics tracking and adaptive layer emphasis. These enhancements enable the identification of stealthy threats that evade traditional TED-based defenses, even in cases of inseparability in topological space and subtle topological perturbations. We review and classify data poisoning tricks in state-of-the-art adaptive attacks and propose enhanced adaptive attack with target mapping, which can dynamically shift malicious tasks and fully leverage the stealthiness that adaptive attacks possess. Our comprehensive experiments on multiple datasets (CIF AR-10, GTSRB, and ImageNet100) and model architectures (ResNet20, ResNet101) show that TED-LaST effectively counteracts sophisticated backdoors like Adap-Blend, Adapt-Patch, and the proposed enhanced adaptive attack. TED-LaST sets a new benchmark for robust backdoor detection, substantially enhancing DNN security against evolving threats. EEP Neural Networks (DNN) models have revolutionized fields such as computer vision [1], speech recognition [2], and autonomous driving [3] with their impressive capabilities. Despite these advances, their dependence on expansive datasets and complex training procedures introduces significant vulnerabilities, notably through backdoor attacks. Backdoor attacks implant hidden behaviors in DNN models, which can be activated by specific triggers.

--With the proliferation of smart grids, smart cities face growing challenges due to cyber-attacks and sophisticated electricity theft behaviors, particularly in residential photovoltaic (PV) generation systems. Traditional Electricity Theft Detection (ETD) methods often struggle to capture complex temporal dependencies and integrating multi-source data, limiting their effectiveness. In this work, we propose an efficient ETD method that accurately identifies fraudulent behaviors in residential PV generation, thus ensuring the supply-demand balance in smart cities. Additionally, we introduce a data embedding technique that seamlessly integrates time-series data with discrete temperature variables, enhancing detection robustness. With the widespread deployment of smart grids, modern power systems are increasingly vulnerable to cyber-attacks and evolving electricity theft behaviors [1].

Android malware presents a persistent threat to users' privacy and data integrity. To combat this, researchers have proposed machine learning-based (ML-based) Android malware detection (AMD) systems. However, adversarial Android malware attacks compromise the detection integrity of the ML-based AMD systems, raising significant concerns. Existing defenses against adversarial Android malware provide protections against feature space attacks which generate adversarial feature vectors only, leaving protection against realistic threats from problem space attacks which generate real adversarial malware an open problem. In this paper, we address this gap by proposing ADD, a practical adversarial Android malware defense framework designed as a plug-in to enhance the adversarial robustness of the ML-based AMD systems against problem space attacks. Our extensive evaluation across various ML-based AMD systems demonstrates that ADD is effective against state-of-the-art problem space adversarial Android malware attacks. Additionally, ADD shows the defense effectiveness in enhancing the adversarial robustness of real-world antivirus solutions.

Patch robustness certification is an emerging kind of defense technique against adversarial patch attacks with provable guarantees. There are two research lines: certified recovery and certified detection. They aim to label malicious samples with provable guarantees correctly and issue warnings for malicious samples predicted to non-benign labels with provable guarantees, respectively. However, existing certified detection defenders suffer from protecting labels subject to manipulation, and existing certified recovery defenders cannot systematically warn samples about their labels. A certified defense that simultaneously offers robust labels and systematic warning protection against patch attacks is desirable. This paper proposes a novel certified defense technique called CrossCert. CrossCert formulates a novel approach by cross-checking two certified recovery defenders to provide unwavering certification and detection certification. Unwavering certification ensures that a certified sample, when subjected to a patched perturbation, will always be returned with a benign label without triggering any warnings with a provable guarantee. To our knowledge, CrossCert is the first certified detection technique to offer this guarantee. Our experiments show that, with a slightly lower performance than ViP and comparable performance with PatchCensor in terms of detection certification, CrossCert certifies a significant proportion of samples with the guarantee of unwavering certification.

Test-time adaptation (TTA) has emerged as a promising solution to address performance decay due to unforeseen distribution shifts between training and test data. While recent TTA methods excel in adapting to test data variations, such adaptability exposes a model to vulnerability against malicious examples, an aspect that has received limited attention. Previous studies have uncovered security vulnerabilities within TTA even when a small proportion of the test batch is maliciously manipulated. In response to the emerging threat, we propose median batch normalization (MedBN), leveraging the robustness of the median for statistics estimation within the batch normalization layer during test-time inference. Our method is algorithm-agnostic, thus allowing seamless integration with existing TTA frameworks. Our experimental results on benchmark datasets, including CIFAR10-C, CIFAR100-C and ImageNet-C, consistently demonstrate that MedBN outperforms existing approaches in maintaining robust performance across different attack scenarios, encompassing both instant and cumulative attacks. Through extensive experiments, we show that our approach sustains the performance even in the absence of attacks, achieving a practical balance between robustness and performance.

Analysing malware is important to understand how malicious software works and to develop appropriate detection and prevention methods. Dynamic analysis can overcome evasion techniques commonly used to bypass static analysis and provide insights into malware runtime activities. Much research on dynamic analysis focused on investigating machine-level information (e.g., CPU, memory, network usage) to identify whether a machine is running malicious activities. A malicious machine does not necessarily mean all running processes on the machine are also malicious. If we can isolate the malicious process instead of isolating the whole machine, we could kill the malicious process, and the machine can keep doing its job. Another challenge dynamic malware detection research faces is that the samples are executed in one machine without any background applications running. It is unrealistic as a computer typically runs many benign (background) applications when a malware incident happens. Our experiment with machine-level data shows that the existence of background applications decreases previous state-of-the-art accuracy by about 20.12% on average. We also proposed a process-level Recurrent Neural Network (RNN)-based detection model. Our proposed model performs better than the machine-level detection model; 0.049 increase in detection rate and a false-positive rate below 0.1.

The problem of revealing botnet activity through Domain Generation Algorithm (DGA) detection seems to be solved, considering that available deep learning classifiers achieve accuracies of over 99.9%. However, these classifiers provide a false sense of security as they are heavily biased and allow for trivial detection bypass. In this work, we leverage explainable artificial intelligence (XAI) methods to analyze the reasoning of deep learning classifiers and to systematically reveal such biases. We show that eliminating these biases from DGA classifiers considerably deteriorates their performance. Nevertheless we are able to design a context-aware detection system that is free of the identified biases and maintains the detection rate of state-of-the art deep learning classifiers. In this context, we propose a visual analysis system that helps to better understand a classifier's reasoning, thereby increasing trust in and transparency of detection methods and facilitating decision-making.

Class incremental learning approaches are useful as they help the model to learn new information (classes) sequentially, while also retaining the previously acquired information (classes). However, it has been shown that such approaches are extremely vulnerable to the adversarial backdoor attacks, where an intelligent adversary can introduce small amount of misinformation to the model in the form of imperceptible backdoor pattern during training to cause deliberate forgetting of a specific task or class at test time. In this work, we propose a novel defensive framework to counter such an insidious attack where, we use the attacker's primary strength-hiding the backdoor pattern by making it imperceptible to humans-against it, and propose to learn a perceptible (stronger) pattern (also during the training) that can overpower the attacker's imperceptible (weaker) pattern. We demonstrate the effectiveness of the proposed defensive mechanism through various commonly used Replay-based (both generative and exact replay-based) class incremental learning algorithms using continual learning benchmark variants of CIFAR-10, CIFAR-100, and MNIST datasets. Most noteworthy, our proposed defensive framework does not assume that the attacker's target task and target class is known to the defender. The defender is also unaware of the shape, size, and location of the attacker's pattern. We show that our proposed defensive framework considerably improves the performance of class incremental learning algorithms with no knowledge of the attacker's target task, attacker's target class, and attacker's imperceptible pattern. We term our defensive framework as Adversary Aware Continual Learning (AACL).