Multimodal Emotion Recognition in Conversations (MERC) identifies utterance emotions by integrating both contextual and multimodal information from dialogue videos. Existing methods struggle to capture emotion shifts due to label replication and fail to preserve positive independent modality contributions during fusion. To address these issues, we propose a Dual Contrastive Learning Framework (DCLF) that enhances current MERC models without additional data. Specifically, to mitigate label replication effects, we construct context-aware contrastive pairs. Additionally, we assign pseudo-labels to distinguish modality-specific contributions. DCLF works alongside basic models to introduce semantic constraints at the utterance, context, and modality levels. Our experiments on two MERC benchmark datasets demonstrate performance gains of 4.67%-4.98% on IEMOCAP and 5.52%-5.89% on MELD, outperforming state-of-the-art approaches. Perturbation tests further validate DCLF’s ability to reduce label dependence. Additionally, DCLF incorporates emotion-sensitive independent modality features and multimodal fusion representations into final decisions, unlocking the potential contributions of individual modalities.

Large Language Models (LLMs) require robust evaluation.However, existing frameworks often rely on curated datasets that, once public, may be accessed by newer LLMs.This creates a risk of data leakage, where test sets inadvertently become part of training data, compromising evaluation fairness and integrity.To mitigate this issue, we propose Behave as Claimed (BaC), a novel evaluation framework inspired by counterfactual reasoning.BaC constructs a "what-if" scenario where LLMs respond to counterfactual questions about how they would behave if the input were manipulated.We refer to these responses as claims, which are verifiable by observing the LLMs' actual behavior when given the manipulated input.BaC dynamically generates and verifies counterfactual questions using various few-shot in-context learning evaluation datasets, reducing their susceptibility to data leakage.Moreover, BaC provides a more challenging evaluation paradigm for LLMs.LLMs must thoroughly understand the prompt, the task, and the consequences of their responses to achieve better performance.We evaluate several LLMs and find that, while most perform well on the original datasets, they struggle with BaC.This suggests that LLMs usually fail to align their claims with their actual behavior and that high performance on standard datasets may be less stable than previously assumed.

The Internet of Vehicles (IoV) has emerged as a key enabler of Intelligent Transportation Systems (ITS), IoV faces significant challenges in scalability and security. The growing volume of real-time vehicular data strains network resources, and traditional centralized architectures introduce single points of failure that compromise reliability and data integrity. This paper investigates the integration of IOTA-a Directed Acyclic Graph (DAG) based distributed ledger designed for feeless and scalable transactions-into the IoV system. In the proposed architecture, vehicles operate as lightweight nodes and roadside units function as full nodes, yielding a resource-efficient architecture for secure, tamper-resistant data interaction across vehicular networks. We formally model the latency of transaction propagation and consensus confirmation phases to gain insight into its performance characteristics under high concurrency. We conducted extensive simulations under diverse traffic conditions on a private IOTAenabled vehicular network. Experimental results demonstrate that the IOTA-based IoV system achieves low latency on the order of a few milliseconds and high throughput of hundreds of transactions per second even as vehicle density increases. The system exhibits strong scalability and operational stability, indicating considerable potential for deployment in real-world ITS environments.

The rapid expansion of Non-Fungible Tokens (NFTs) ecosystem in Web 3.0 service has produced complex transaction networks that challenge traditional graph analysis methods. To address these limitations, this paper presents a higher-order network framework for modeling and analyzing NFT transaction data. Our approach constructs a multi-layered representation of the NFT ecosystem by integrating temporal hypergraphs and motif-based networks, thereby capturing multiway interactions and temporal dependencies beyond simple pairwise transactions. We target three specific tasks to uncover and leverage latent dependencies in NFT markets. First, we build a temporal hypergraph and motif-based network to encode multientity, multi-token relationships. Next, we develop a Higher-Order Graph Neural Network that incorporates token ownership chains and motif edges to improve node classification, significantly outperforming traditional model in identifying key actor roles. Finally, we propose a link prediction model that integrates shared-token and motif-based features, substantially enhancing accuracy in forecasting new NFT transactions compared to baseline models. Our findings validate that explicitly capturing higher-order dependencies is crucial for robust and interpretable analysis of NFT ecosystems, facilitating better Web 3.0 service.

Stacked AutoEncoders (SAE) have been widely adopted in edge anomaly detection scenarios. However, the resource-intensive nature of SAE can pose significant challenges for edge devices, which are typically resource-constrained and must adapt rapidly to dynamic and changing conditions. Optimizing SAE to meet the heterogeneous demands of real-world deployment scenarios, including high performance under constrained storage, low power consumption, fast inference, and efficient model updates, remains a substantial challenge. To address this, we propose an integrated optimization framework that jointly considers these critical factors to achieve balanced and adaptive system-level optimization. Specifically, we formulate SAE optimization for edge anomaly detection as a multi-objective optimization problem and propose MO-SAE (Multi-Objective Stacked AutoEncoders). The multiple objectives are addressed by integrating model clipping, multi-branch exit design, and a matrix approximation technique. In addition, a multi-objective heuristic algorithm is employed to effectively balance the competing objectives in SAE optimization. Our results demonstrate that the proposed MO-SAE delivers substantial improvements over the original approach. On the x86 architecture, it reduces storage space and power consumption by at least 50%, improves runtime efficiency by no less than 28%, and achieves an 11.8% compression rate, all while maintaining application performance. Furthermore, MO-SAE runs efficiently on edge devices with ARM architecture. Experimental results show a 15% improvement in inference speed, facilitating efficient deployment in cloud–edge collaborative anomaly detection systems.

The Multi-Party Conversation (MPC) system has gained attention for its relevance in modern communication. Recent work has focused on developing specialized models for different MPC subtasks, improving state-of-the-art (SOTA) performance. However, since MPC demands often arise collaboratively, managing multiple specialized models is impractical. Additionally, dialogue evolves through diverse meta-information, where knowledge from specific subtasks can influence others. To address this, we propose UniMPC, a unified framework that consolidates common MPC subtasks. UniMPC uses a graph network with utterance nodes, a global node for combined local and global information, and two adaptable free nodes. It also incorporates discourse parsing to enhance model updates. We introduce MPCEval, a new benchmark for evaluating MPC systems. Experiments show UniMPC achieves over 95% of SOTA performance across all subtasks, with some surpassing existing SOTA, highlighting the effectiveness of the global node, free nodes, and dynamic discourse-aware graphs.

With the advancement of blockchain technology, its application in data management and query processing has garnered increasing attention. However, as a distributed database system, blockchain currently falls short in supporting diverse data query requirements. Skyline computation, which identifies Pareto optimal solutions in multi-dimensional data, has become an increasingly necessary feature in blockchain environments. Traditional skyline computation methods struggle with inefficiency when handling large-scale and multi-dimensional data, and they lack effective verification mechanisms within a blockchain context. This paper proposes a multi-dimensional data index structure for skyline computation based on a hybrid blockchain architecture of full nodes and light nodes, utilizing Merkle tree and B+ tree. Additionally, an early pruning-based divide-and-conquer strategy is designed based on this index structure. This approach optimizes the skyline query process by computing local skylines to derive the global skyline. Simultaneously, by introducing Bloom filter, we reduce unnecessary I/O operations during result verification, enabling light nodes to perform verification operations more efficiently. Extensive experiments have demonstrated the effectiveness of our proposed scheme, which can improve query speed by an average of 90.08% compared to the BNL algorithm and by an average of 86.12% compared to the SFS algorithm.

In recent years, neural networks have achieved impressive performance on dialogue response generation. However, most of these models still suffer from some shortcomings, such as yielding uninformative responses and lacking explainable ability. This article proposes a Two-stage Dialogue Response Generation model (TSRG), which specifies a method to generate diverse and informative responses based on an interpretable procedure between stages. TSRG involves a two-stage framework that generates a candidate response first and then instantiates it as the final response. The positional information and a resident token are injected into the candidate response to stabilize the multi-stage framework, alleviating the shortcomings in the multi-stage framework. Additionally, TSRG allows adjusting and interpreting the interaction pattern between the two generation stages, making the generation response somewhat explainable and controllable. We evaluate the proposed model on three dialogue datasets that contain millions of single-turn message-response pairs between web users. The results show that, compared with the previous multi-stage dialogue generation models, TSRG can produce more diverse and informative responses and maintain fluency and relevance.

Cross-core cache timing side-channel attacks, which observe cache access behavior of victims running on different physical cores to infer sensitive information, have become a significant threat. Although the attacks are covert, they cause the attacked cachelines to frequently migrate among cache hierarchies, rendering abnormal traffic. Based on this observation, the proposed scheme PiPoMonitor records cache-memory access traffic and prefetch suspicious lines under attack to interfere with adversaries’ probes. In pursuit of security and performance, PiPoMonitor exploits a Cuckoo filter as the recording structure and introduces two features to it: 1) autonomic deletion and 2) relocation accelerating. The former exponentially increases the uncertainty of record eviction against reverse engineering attacks, while the latter leverages a pipelined architecture to alleviate the impact of intensive filter queries on the memory critical path. PiPoMonitor is not only able to effectively mitigate cross-core cache attacks and defeat sophisticated defense-aware attackers but also induces a negligible performance penalty and acceptable hardware overhead.

Previous works show that Pre-trained Language Models (PLMs) can capture factual knowledge.However, some analyses reveal that PLMs fail to perform it robustly, e.g., being sensitive to the changes of prompts when extracting factual knowledge.To mitigate this issue, we propose to let PLMs learn the deterministic relationship between the remaining context and the masked content.The deterministic relationship ensures that the masked factual content can be deterministically inferable based on the existing clues in the context.That would provide more stable patterns for PLMs to capture factual knowledge than randomly masking.Two pre-training tasks are further introduced to motivate PLMs to rely on the deterministic relationship when filling masks.Specifically, we use an external Knowledge Base (KB) to identify deterministic relationships and continuously pre-train PLMs with the proposed methods.The factual knowledge probing experiments indicate that the continuously pre-trained PLMs achieve better robustness in factual knowledge capturing.Further experiments on question-answering datasets show that trying to learn a deterministic relationship with the proposed methods can also help other knowledge-intensive tasks.

The recent surges in the open conversational data caused Emotion Recognition in Spoken Dialog (ERSD) to gain much attention. However, the existing ERSD datasets’ scale limits the model’s complete reasoning. Moreover, the artificial dialogue agent is ideally able to reference past dialogue experiences. This paper proposes a Commonsense Knowledge Enhanced Network with a retrospective loss, namely CKE-Net, to hierarchically perform dialog modeling, external knowledge integration, and historical state retrospect. Specifically, we first adopt a transformer-based encoder to model context in multi-view by elaborating different mask matrices. Then, the graph attention network is used to introduce commonsense knowledge, which benefits the complex emotional reasoning. Finally, a retrospective loss is added to utilize the model’s prior experience during training. Experiments on IEMOCAP and MELD datasets demonstrate that every designed module is consistently beneficial to the performance. Extensive experimental results show that our model outperforms the state-of-the-art models across the two benchmark datasets.

Collecting supporting evidence from large corpora of text (e.g., Wikipedia) is of great challenge for open-domain Question Answering (QA). Especially, for multi-hop open-domain QA, scattered evidence pieces are required to be gathered together to support the answer extraction. In this paper, we propose a new retrieval target, hop, to collect the hidden reasoning evidence from Wikipedia for complex question answering. Specifically, the hop in this paper is defined as the combination of a hyperlink and the corresponding outbound link document. The hyperlink is encoded as the mention embedding which models the structured knowledge of how the outbound link entity is mentioned in the textual context, and the corresponding outbound link document is encoded as the document embedding representing the unstructured knowledge within it. Accordingly, we build HopRetriever which retrieves hops over Wikipedia to answer complex questions. Experiments on the HotpotQA dataset demonstrate that HopRetriever outperforms previously published evidence retrieval methods by large margins. Moreover, our approach also yields quantifiable interpretations of the evidence collection process.

Continuous Attacks are common cross-core cache side-channel attack scenarios that we observed, where adversaries frequently probe-target cache lines in a short time. Under Continuous Attacks, the attacked lines go through multiple load-evict processes between different cache (or memory) hierarchies, exhibiting Ping-Pong patterns. Identifying and obscuring these abnormal patterns effectively interfere with the attacker's probe and mitigate such attacks. Our recent proposal, Ping-Pong regulator (PPR), captures multiple Ping-Pong patterns by counting the reaccesses per cache line and blocks them with different obscuring actions (preload or lock). Although PPR mitigates Continuous Attacks, the added regulator directory (RDir) is vulnerable because it cannot record all cache lines simultaneously. Sophisticated attackers can evict the records of the attacked line from the RDir to avoid triggering defensive actions, thereby bypassing PPR. To improve robustness, we further propose PPR+, which dynamically changes the mapping of physical addresses to RDir locations by encryption and periodically changing keys. This randomness makes it difficult for attackers to evict target entries out of the RDir within a limited time. We show that PPR+ tolerates more than 100 years of attacks, induces negligible performance impacts (improves 0.13%), requires acceptable storage overhead (3.15%), and does not need any software support.

In this paper, we observed Continuous Attacks are one kind of common side channel attack scenarios, where an adversary frequently probes the same target cache lines in a short time. Continuous Attacks cause target cache lines to go through multiple load-evict processes, exhibiting Ping-Pong Patterns. Identifying and obscuring Ping-Pong Patterns effectively interferes with the attacker’s probe and mitigates Continuous Attacks. Based on the observations, this paper proposes Ping-Pong Regulator to identify multiple Ping-Pong Patterns and block them with different strategies (Preload or Lock). The Preload proactively loads target lines into the cache, causing the attacker to mistakenly infer that the victim has accessed these lines; the Lock fixes the attacked lines’ directory entries on the last level cache directory until they are evicted out of caches, making an attacker’s observation of the locked lines is always the L2 cache miss. The experimental evaluation demonstrates that the Ping-Pong Regulator efficiently identifies and secures attacked lines, induces negligible performance impacts and storage overhead, and does not require any software support.

Modern processor cores share the last-level cache and directory to improve resource utilization. Unfortunately, such sharing makes the cache vulnerable to cross-core cache side channel attacks. Recent studies show that information leakage through cross-core cache side channel attacks is a serious threat in different computing domains ranging from cloud servers and mobile phones to embedded devices. However, previous solutions have limitations of losing performance, lacking golden standards, requiring software support, or being easily bypassed.

Address-resolution protocol (ARP) is an important protocol of data link layers that aims to obtain the corresponding relationship between Internet Protocol (IP) and Media Access Control (MAC) addresses. Traditional ARPs (address-resolution and neighbor-discovery protocols) do not consider the existence of malicious nodes, which reveals destination addresses in the resolution process. Thus, these traditional protocols allow malicious nodes to easily carry out attacks, such as man-in-the-middle attack and denial-of-service attack. To overcome these weaknesses, we propose an anonymous-address-resolution (AS-AR) protocol. AS-AR does not publicize the destination address in the address-resolution process and hides the IP and MAC addresses of the source node. The malicious node cannot obtain the addresses of the destination and the node which initiates the address resolution; thus, it cannot attack. Analyses and experiments show that AS-AR has a higher security level than existing security methods, such as secure-neighbor discovery.

Memory race recording has been proved to be a hard problem in multithreaded deterministic record-replay. It is important to develop an efficient memory race recording algorithm. However, most of the prior work tries to record all memory conflicts, whether they affect deterministic replay or not, resulting a relatively large memory race log. This paper proposes an innovative synchronization aware point-to-point memory race recorder, called SAMR. SAMR analyzes memory conflicts introduced by synchronization operations and classifies them into harmful synchronization conflicts and harmless synchronization conflicts. Harmless synchronization conflicts are filtered out by identifying synchronization operations when recording, and a reduced memory race log is achieved. At the same time, SAMR reduces hardware overhead by using signatures instead of cache memory. Simulations with splash-2 workloads on 8-core CMP system show that SAMR can achieve small memory race size (~2 bytes per thousand memory instructions), good scalability in log size and low bandwidth overhead (<; 5%), while not needing too much hardware state (~1129 bytes).

Shared-memory multithreaded programs running on chip multiprocessors (CMPs) tend to be nondeterministic. Two-phase deterministic record-replay is an effective approach to solve this nondeterminism. This paper proposes an efficient deterministic record-replay named Fly Replay. During recording, Fly Replay logs not only the right dependencies of memory races but also the pseudo dependencies constituted by predecessors of memory races into per-thread log. During replay, Fly Replay produces wakeup messages actively to trigger successors in time, achieving low communication overhead and fast replay speed. At the same time, Fly Replay reduces hardware overhead by using hardware signatures. Simulation shows that Fly Replay reduces the log size for splash2 workloads by 40% on average compared with RTR and Rerun in 4-core systems, and has good scalability in log size. More importantly, Fly Repaly can achieve replay speed within 1%~18% of the native execution speed without record-replay.

The use of peer-to-peer (P2P) applications is growing dramatically, particularly for BitTorrent system. In order to gain insights into BitTorrent systems and the network traffic load they place on ISPs, we have undertaken an measurement study. Our experimental evaluation is ISP oriented instead of peer oriented, which enables us to study the global characteristics of BitTorrent system. We have developed a dedicated BitTorrent sniffer platform to collected extensive packet across a large ISP network. The measurement results bring important insights into BitTorrent systems. Specifically,our results show that 1) BitTorrent flashcrowd appears around midnight due to the BitTorrent users habits of behavior; 2) workload generated by BitTorrent extention - DHT is much more than it generated by calssic BitTorrent; 3) overhead rather than data transfer is the dominant component of the totle BitTorrent traffic due to DHT; 4) Zipf and pareto are the suitable model to characterize the distribution of visits to both trackers and BitTorrent Websites.Insights obtained in this study will be valuable for the management and development of future P2P file transform systems.