Adversarial Security of Financial Language Models (ASFLM) is critical as Large Language Models (LLMs) pervade high-stakes financial applications. However, LLMs face two key challenges: their vulnerability to damaging adversarial attacks and the prevalent research gap concerning robust defenses against sophisticated, semantically coherent threats. To address these, we first theoretically analyze the relationship between discrete and continuous adversarial optimization, proving the continuous optimum provides a lower bound for the discrete. This foundation supports our novel two-stage framework, ChameleonAttack. It employs Adaptive Latent-space Optimization (ALO) for potent adversarial token discovery, followed by a Semantic-Translation Module (STM) module to generate fluent, coherent, and natural-sounding adversarial text. This dual approach aims to maximize attack impact while ensuring high linguistic quality and semantic integrity for evasion. Evaluated on state-of-the-art financial LLMs (e.g., FinBERT) and standard benchmarks (e.g., Financial PhraseBank), ChameleonAttack achieves a high Attack Success Rate (ASR) of 93.4%. These results highlight significant practical vulnerabilities and underscore the urgent need for robust defense mechanisms in the financial domain.

The Polymorphic Network (PINet) is a future network architecture that can dynamically load multiple network modalities (NM), solving the rigidity and single IP bearer problem. However, due to the different design concepts and protocol stacks of each NM, it is challenging to provide compatible data access control for different NMs. In this paper, we propose a unified attribute-based data access control framework within PINet. This framework ensures consistent access control across NMs by managing user attribute identifiers and seamlessly integrating access policies. We design Span-hiding Cipher-policy Attribute-based Encryption (SHCP-ABE). The design of span attribute cuckoo filter and two-round encryption in SHCP-ABE implements access control that supports comparing attribute values and policy hiding. We further modified the linear secret sharing scheme in SHCP-ABE to achieve isolation of access policy information among NMs. The proposed SHCP-ABE scheme is unified, fine-grained, privacy-preserving, and can effectively adapt to heterogeneous future network architectures such as PINet. Security analysis shows that SHCP-ABE is secure against the adaptive chosen plaintext attack under the generic group model. Experimental results show that SHCP-ABE reduces the time overhead of key generation and decryption and the key storage overhead by about 50% over the existing comparable CP-ABE scheme, providing excellent efficiency.

Multilingual audio-text retrieval (ML-ATR) is a challenging task that aims to retrieve audio clips or multilingual texts from databases. However, existing ML-ATR schemes suffer from inconsistencies for instance similarity matching across languages. To address the inconsistency issue in multilingual audio-text retrieval, we first identify two intuitive factors that contribute to inconsistency: misalignment between audio and multilingual text embeddings, and error propagation in model optimization. By systematically analyzing these factors, we derive theoretical weight error upper bounds for quantifying their effects and find that the main source of inconsistency is the data distribution error during training. This finding motivates our solution to reduce data distribution errors.We propose a consistent ML-ATR scheme using 1-to-k contrastive learning and audio-English co-anchor contrastive learning, aiming to mitigate the negative impact of data distribution error on recall and consistency in ML-ATR. Experimental results on the translated AudioCaps and Clotho datasets show that our scheme achieves state-of-the-art performance on recall and consistency metrics for eight mainstream languages, including English. Our code will be available at https://github.com/ATRI-ACL/ATRI-ACL.

Multimodal Large Language Models (MLLMs), which integrate vision and other modalities into Large Language Models (LLMs), significantly enhance AI capabilities but also introduce new security vulnerabilities. By exploiting the vulnerabilities of the visual modality and the long-tail distribution characteristic of code training data, we present PiCo, a novel jailbreaking framework designed to progressively bypass multi-tiered defense mechanisms in advanced MLLMs. PiCo employs a tier-by-tier jailbreak strategy, using token-level typographic attacks to evade input filtering and embedding harmful intent within programming context instructions to bypass runtime monitoring. To comprehensively assess the impact of attacks, a new evaluation metric is further proposed to assess both the toxicity and helpfulness of model outputs post-attack. By embedding harmful intent within code-style visual instructions, PiCo achieves an average Attack Success Rate (ASR) of 84.13% on Gemini-Pro Vision and 52.66% on GPT-4, surpassing previous methods. Experimental results highlight the critical gaps in current defenses, underscoring the need for more robust strategies to secure advanced MLLMs. Content Warning: This paper contains examples that may be offensive.

With its wide range of applications, the Internet shows a future trend towards abundant and diverse data resources with multiple types of identifiers (multi-identifiers). However, the legacy Domain Name System (DNS) in the current TCP/IP network architecture has failed to manage these identifiers due to the centralized security issue. While some decentralized DNS alternatives have been proposed, they also face scalability issues. In this paper, we propose a blockchain-based Hierarchical Multi-Identifier System, named H-MIS, as a DNS alternative. Specially, it realizes optimal decentralization and scalability by introducing the Zero-Knowledge rollup (ZK-rollup) solution to synchronize the upper and lower on-chain identifier data, as well as off-chain associated resource data. Finally, we implement H-MIS on Ethereum and evaluate its performance. The experimental results indicate that compared to the original MIS and Ethereum Name Service (ENS), H-MIS has advantages in such aspects as efficiency, data consumption, and Gas fees.