The rapid advancement of multimodal large language models (MLLMs) has led to breakthroughs in various applications, yet their security remains a critical challenge. One pressing issue involves unsafe image-query pairs--jailbreak inputs specifically designed to bypass security constraints and elicit unintended responses from MLLMs. Compared to general multimodal data, such unsafe inputs are relatively sparse, which limits the diversity and richness of training samples available for developing robust defense models. Meanwhile, existing guardrail-type methods rely on external modules to enforce security constraints but fail to address intrinsic vulnerabilities within MLLMs. Traditional supervised fine-tuning (SFT), on the other hand, often over-refuses harmless inputs, compromising general performance. Given these challenges, we propose Secure Tug-of-War (SecTOW), an innovative iterative defense-attack training method to enhance the security of MLLMs. SecTOW consists of two modules: a defender and an auxiliary attacker, both trained iteratively using reinforcement learning (GRPO). During the iterative process, the attacker identifies security vulnerabilities in the defense model and expands jailbreak data. The expanded data are then used to train the defender, enabling it to address identified security vulnerabilities. We also design reward mechanisms used for GRPO to simplify the use of response labels, reducing dependence on complex generative labels and enabling the efficient use of synthetic data. Additionally, a quality monitoring mechanism is used to mitigate the defender's over-refusal of harmless inputs and ensure the diversity of the jailbreak data generated by the attacker. Experimental results on safety-specific and general benchmarks demonstrate that SecTOW significantly improves security while preserving general performance.

Text-to-image diffusion models show remarkable generation performance following text prompts, but risk generating Not Safe For Work (NSFW) contents from unsafe prompts. Existing approaches, such as prompt filtering or concept unlearning, fail to defend against adversarial attacks while maintaining benign image quality. In this paper, we propose a novel approach called Distorting Embedding Space (DES), a text encoder-based defense mechanism that effectively tackles these issues through innovative embedding space control. DES transforms unsafe embeddings, extracted from a text encoder using unsafe prompts, toward carefully calculated safe embedding regions to prevent unsafe contents generation, while reproducing the original safe embeddings. DES also neutralizes the nudity embedding, extracted using prompt ``nudity", by aligning it with neutral embedding to enhance robustness against adversarial attacks. These methods ensure both robust defense and high-quality image generation. Additionally, DES can be adopted in a plug-and-play manner and requires zero inference overhead, facilitating its deployment. Extensive experiments on diverse attack types, including black-box and white-box scenarios, demonstrate DES's state-of-the-art performance in both defense capability and benign image generation quality. Our model is available at https://github.com/aei13/DES.

Graph neural networks (GNNs) have become instrumental in diverse real-world applications, offering powerful graph learning capabilities for tasks such as social networks and medical data analysis. Despite their successes, GNNs are vulnerable to adversarial attacks, including membership inference attacks (MIA), which threaten privacy by identifying whether a record was part of the model's training data. While existing research has explored MIA in GNNs under graph inductive learning settings, the more common and challenging graph transductive learning setting remains understudied in this context. This paper addresses this gap and proposes an effective two-stage defense, Graph Transductive Defense (GTD), tailored to graph transductive learning characteristics. The gist of our approach is a combination of a train-test alternate training schedule and flattening strategy, which successfully reduces the difference between the training and testing loss distributions. Extensive empirical results demonstrate the superior performance of our method (a decrease in attack AUROC by $9.42\%$ and an increase in utility performance by $18.08\%$ on average compared to LBP), highlighting its potential for seamless integration into various classification models with minimal overhead.

Although safely enhanced Large Language Models (LLMs) have achieved remarkable success in tackling various complex tasks in a zero-shot manner, they remain susceptible to jailbreak attacks, particularly the unknown jailbreak attack. To enhance LLMs' generalized defense capabilities, we propose a two-stage adversarial tuning framework, which generates adversarial prompts to explore worst-case scenarios by optimizing datasets containing pairs of adversarial prompts and their safe responses. In the first stage, we introduce the hierarchical meta-universal adversarial prompt learning to efficiently and effectively generate token-level adversarial prompts. In the second stage, we propose the automatic adversarial prompt learning to iteratively refine semantic-level adversarial prompts, further enhancing LLM's defense capabilities. We conducted comprehensive experiments on three widely used jailbreak datasets, comparing our framework with six defense baselines under five representative attack scenarios. The results underscore the superiority of our proposed methods. Furthermore, our adversarial tuning framework exhibits empirical generalizability across various attack strategies and target LLMs, highlighting its potential as a transferable defense mechanism.

Recent studies reveal that Large Language Models (LLMs) face challenges in balancing safety with utility, particularly when processing long texts for NLP tasks like summarization and translation. Despite defenses against malicious short questions, the ability of LLMs to safely handle dangerous long content, such as manuals teaching illicit activities, remains unclear. Our work aims to develop robust defenses for LLMs in processing malicious documents alongside benign NLP task queries. We introduce a defense dataset comprised of safety-related examples and propose single-task and mixed-task losses for instruction tuning. Our empirical results demonstrate that LLMs can significantly enhance their capacity to safely manage dangerous content with appropriate instruction tuning. Additionally, strengthening the defenses of tasks most susceptible to misuse is effective in protecting LLMs against processing harmful information. We also observe that trade-offs between utility and safety exist in defense strategies, where Llama2, utilizing our proposed approach, displays a significantly better balance compared to Llama1.

Large language models (LLMs) are susceptible to red teaming attacks, which can induce LLMs to generate harmful content. Previous research constructs attack prompts via manual or automatic methods, which have their own limitations on construction cost and quality. To address these issues, we propose an integrated approach that combines manual and automatic methods to economically generate high-quality attack prompts. Specifically, considering the impressive capabilities of newly emerged LLMs, we propose an attack framework to instruct LLMs to mimic human-generated prompts through in-context learning. Furthermore, we propose a defense framework that fine-tunes victim LLMs through iterative interactions with the attack framework to enhance their safety against red teaming attacks. Extensive experiments on different LLMs validate the effectiveness of our proposed attack and defense frameworks. Additionally, we release a series of attack prompts datasets named SAP with varying sizes, facilitating the safety evaluation and enhancement of more LLMs. Our code and dataset is available on https://github.com/Aatrox103/SAP .

Deep learning technology has made great achievements in the field of image. In order to defend against malware attacks, researchers have proposed many Windows malware detection models based on deep learning. However, deep learning models are vulnerable to adversarial example attacks. Malware can generate adversarial malware with the same malicious function to attack the malware detection model and evade detection of the model. Currently, many adversarial defense studies have been proposed, but existing adversarial defense studies are based on image sample and cannot be directly applied to malware sample. Therefore, this paper proposes an adversarial malware defense method based on adversarial training. This method uses preprocessing to defend simple adversarial examples to reduce the difficulty of adversarial training. Moreover, this method improves the adversarial defense capability of the model through adversarial training. We experimented with three attack methods in two sets of datasets, and the results show that the method in this paper can improve the adversarial defense capability of the model without reducing the accuracy of the model.

The Cabinet approved a defense budget Friday of ¥5.40 trillion ($47 billion) for fiscal 2022, setting a record high for the eighth consecutive year, to advance the development of new technologies in the face of China's growing military might and the North Korean nuclear threat. The draft budget, including outlays for hosting U.S. military bases, rose 1.1% from the current fiscal year ending in March as Japan ramps up its defense capabilities. The increase for a 10th year in a row is largely attributable to a sharp rise in research and development spending, for which the Defense Ministry has earmarked ¥291.1 billion, up ¥79.6 billion, or 37.6%, from a year earlier. The ministry will invest in advanced technologies, such as crewless planes that use artificial intelligence to fly in teams with next-generation fighter jets. "As the security environment surrounding Japan has been changing at an unprecedented speed and becoming increasingly severe, it is an urgent task for Japan to strengthen its necessary defense capabilities," Defense Minister Nobuo Kishi said at a news conference.

DGIST announced on Tuesday, July 16 that Senior Researcher Dae-gun Oh's team in the Collaborative Robots Research Center developed a radar system that can detect subminiature drones that are 3km away. This research is expected to make huge contributions to strengthening domestic industries and defense capabilities by securing a world-class radar sensing technology. As a result of discovering a North Korean drone in Paju in March 2014, South Korea's Ministry of National Defense has adopted a drone detection radar based on an overseas technology. Since last year, the ministry has devoted itself into building a combat system using drones and training specialized personnel by forming a drone unit to strengthen its defense capability. The necessity of enemy surveillance reconnaissance and the early detection of offensive drones has increased in Korea.