Transfer learning, successful in knowledge translation across related tasks, faces a substantial privacy threat from membership inference attacks (MIAs). These attacks, despite posing significant risk to ML model’s training data, remain limited-explored in transfer learning. The interaction between teacher and student models in transfer learning has not been thoroughly explored in MIAs, potentially resulting in an under-examined aspect of privacy vulnerabilities within transfer learning. In this paper, we propose a new MIA vector against transfer learning, to determine whether a specific data point was used to train the teacher model while only accessing the student model in a white-box setting. Our method delves into the intricate relationship between teacher and student models, analyzing the discrepancies in hidden layer representations between the student model and its shadow counterpart. These identified differences are then adeptly utilized to refine the shadow model’s training process and to inform membership inference decisions effectively. Our method, evaluated across four datasets in diverse transfer learning tasks, reveals that even when an attacker only has access to the student model, the teacher model’s training data remains susceptible to MIAs. We believe our work unveils the unexplored risk of membership inference in transfer learning.

In the era of zero trust security models and next-generation networks (NGN), the primary challenge is that network nodes may be untrusted, even if they have been verified, necessitating continuous validation and scrutiny. Effective intrusion detection systems (IDS) are crucial for continuously monitoring network traffic and identifying potential threats. However, traditional IDS approaches often struggle to keep pace with evolving threats, requiring extensive supervised training on labeled datasets. This limitation leads to high false positive rates, low detection accuracy, and a failure to provide real-time detection, thereby undermining the security of NGNs. This paper proposed the first self-supervised learning-based IDS, designed on temporal contrastive graph neural network (GNN), namely TCG-IDS. It innovatively integrates three contrastive learning strategies: temporal contrasting to capture temporal dependencies, asymmetric contrasting to account for the diverse interactions within network data, and masked contrasting to enhance the learning of node representations by masking parts of the data during training. Performance evaluation was conducted on two publicly available network traffic datasets, NF-CSE-CIC-IDS2018-V2 and NF-UNSW-NB15-V2. TCG-IDS achieved a balanced accuracy of 99.48% and 91.48% on two datasets respectively, significantly outperforming state-of-the-art graph learning models. In multi-class detection, TCG-IDS attained a mean false positive rate of 4.15% and 3.34% on the two datasets respectively. Besides, it exhibits high efficiency with its running time of 0.37s and 0.51s on the two datasets to predict per batch of 100 samples. Results highlight the effectiveness and efficiency of TCG-IDS in accurately detecting various types of network intrusions. This work significantly advances the field of network intrusion detection via self-supervised temporal graph learning, offering a promising solution for future network security systems.

Smart contracts, the cornerstone of decentralized applications, have become increasingly prominent in revolutionizing the digital landscape. However, vulnerabilities in smart contracts pose great risks to user assets and undermine overall trust in decentralized systems. Fuzzing, a prominent security testing technique, is extensively explored to detect vulnerabilities. But current smart contract fuzzers fall short of expectations in testing efficiency for two primary reasons. Firstly, smart contracts are stateful programs, and existing approaches, primarily coverage-guided, lack effective feedback from the contract state. Consequently, they struggle to effectively explore the contract state space. Secondly, coverage-guided fuzzers, aiming for comprehensive program coverage, may lead to a wastage of testing resources on benign code areas. This wastage worsens in smart contract testing, as the mix of code and state spaces further complicates comprehensive testing. To address these challenges, we propose VULSEYE, a stateful directed graybox fuzzer for smart contracts guided by vulnerabilities. Different from prior works, VULSEYE achieves stateful directed fuzzing by prioritizing testing resources to code areas and contract states that are more prone to vulnerabilities. We introduce Code Targets and State Targets into fuzzing loops as the testing targets of VULSEYE. We use static analysis and pattern matching to pinpoint Code Targets, and propose a scalable backward analysis algorithm to specify State Targets. We design a novel fitness metric that leverages feedback from both the contract code space and state space, directing fuzzing toward these targets. With the guidance of code and state targets, VULSEYE alleviates the wastage of testing resources on benign code areas and achieves effective stateful fuzzing. In comparison with state-of-the-art fuzzers, VULSEYE demonstrated superior effectiveness and efficiency. Notably, it uncovered 4,845 vulnerabilities in 42,738 real-world smart contracts, outperforming existing approaches by up to 9.7×, and identified 11 previously unknown vulnerabilities within the top 50 Ethereum DApps, involving approximately 2,500,000 USD.

Ponzi schemes, a form of scam, have been discovered in Ethereum smart contracts in recent years, causing massive financial losses. Rule-based detection approaches rely on pre-defined rules with limited capabilities and domain knowledge dependency. Additionally, using static information like opcodes and transactions for machine learning models fails to effectively characterize the Ponzi contracts, resulting in poor reliability and interpretability. In this paper, we propose PonziGuard, an efficient Ponzi scheme detection approach based on contract runtime behavior. Inspired by the observation that a contract's runtime behavior is more effective in disguising Ponzi contracts from the innocent contracts, PonziGuard establishes a comprehensive graph representation called contract runtime behavior graph (CRBG), to accurately depict the behavior of Ponzi contracts. Furthermore, it formulates the detection process as a graph classification task, enhancing its overall effectiveness. We conducted comparative experiments on a ground-truth dataset and applied PonziGuard to Ethereum Mainnet. The results show that PonziGuard outperforms the current state-of-the-art approaches and is also effective in open environments. Using PonziGuard, we have identified 805 Ponzi contracts on Ethereum Mainnet, which have resulted in an estimated economic loss of 281,700 Ether or approximately $500 million USD.

Web application firewall (WAF) examines malicious traffic to and from a web application via a set of security rules. It plays a significant role in securing Web applications against web attacks. However, as web attacks grow in sophistication, it is becoming increasingly difficult for WAFs to block the mutated malicious payloads designed to bypass their defenses. In response to this critical security issue, we have developed a novel learning-based framework called WAFBOOSTER, designed to unveil potential bypasses in WAF detections and suggest rules to fortify their security. Using a combination of shadow models and payload generation techniques, we can identify malicious payloads and remove or modify them as needed. WAFBOOSTER generates signatures for these malicious payloads using advanced clustering and regular expression matching techniques to repair any security gaps we uncover. In our comprehensive evaluation of eight real-world WAFs, WAFBOOSTER improved the true rejection rate of mutated malicious payloads from 21% to 96%, with no false rejections. WAFBOOSTER achieves a false acceptance rate 3× lower than state-of-the-art methods for generating malicious payloads. With WAFBOOSTER, we have taken a step forward in securing web applications against the ever-evolving threats.

Decentralized finance has experienced phenomenal growth, revolutionizing the landscape of financial transactions and asset management via blockchain. Yet, this swift growth brings with it substantial challenges, notably the surge in scam tokens, imposing significant security threats on cryptocurrency investments and trading. Existing detection methods of scam token, primarily relying on analyzing contract codes or transaction patterns, struggle to catch increasingly sophisticated tactics employed by scammers. For example, contract-based analysis are unable to identify scams lacking overt malicious code, e.g., most rugpulls, while transaction-based methods generally lack the foresight to early-detect potential risks. In this paper, we present TokenScout, the first temporal temporal graph neural network-based framework for scam token early detection. TokenScout formulates token transfer data as a dynamic temporal attributed multigraph and leverages the temporal graph learning model to learn graph representations. It also builds a graph representation refining model based on contrastive learning to learn a more discriminative representation space for risk identification. We evaluated TokenScout using a comprehensive dataset of 214,084 standard ERC20 tokens from 2015 to February 2023. TokenScout achieves a balanced accuracy of 98.41%. Additionally, from March to May 2023, deploying TokenScout on Ethereum effectively identified 706 rugpulls, 174 honeypots, and 90 Ponzi schemes, thereby alerting to potential risks exceeding 240 million.