NSTL国家科技图书文献中心

1. An Effective Ensemble Algorithm for Short-Term Load Forecasting NSTL国家科技图书文献中心

En-Wei Zhang | Luo-Fan Wu ... - 《Information Security Applications》 - International Conference on Information Security Applications - 2025, - 164～176 - 共13页

摘要：Short-term load forecasting (STLF) is a | critical issue for managing electricity distribution | systems because its accuracy might strongly impact the | performance and security of the power system. An effective | load forecasting system, of course, can also be used

关键词： Smart grid | Deep learning | Machine learning

2. PUF-Based Authentication and Authorization Protocol for IoT NSTL国家科技图书文献中心

Yu-Tse Shih | Shih-Ming Huang ... - 《Information Security Applications》 - International Conference on Information Security Applications - 2025, - 179～190 - 共12页

摘要：With the rapid development of technology | , smart devices have become indispensable tools for | people, and IoT devices are ubiquitous, playing an | important role in our daily lives. When using IoT device | applications and services, users must go through complex

关键词： Physically unclonable functions | Authentication | Authorization | Key exchange | Internet of things

3. A Survey on Attack Cases with VBS Malware in Windows NSTL国家科技图书文献中心

GyuHyun Jeon | Seungho Jeon ... - 《Information Security Applications》 - International Conference on Information Security Applications - 2025, - 284～296 - 共13页

摘要：Visual Basic Script (VBS)-based malicious code | exists in various forms such as document type | , executable file, and LNK file. After disguising it as a | normal file or exploiting a vulnerability to trick the | user into executing it, malicious actions are

关键词： Malware | VBS | Windows | Case analysis | MITRE ATT&CK

4. VoteGAN: Generalized Membership Inference Attack Against Generative Models by Multiple Discriminators NSTL国家科技图书文献中心

Gyeongsup Lim | Wonjun Oh ... - 《Information Security Applications》 - International Conference on Information Security Applications - 2025, - 71～82 - 共12页

摘要：Generative Adversarial Networks (GANs | ) produces samples with the same probability distribution | as the given training data. However, as they | frequently train with sensitive data to generate realistic | samples, many people are concerned about the leakage of

关键词： AI security | Machine learning | Computer vision

5. Boosting Black-Box Transferability of Weak Audio Adversarial Attacks with Random Masking NSTL国家科技图书文献中心

Mai Bui | Thien-Phuc Doan ... - 《Information Security Applications》 - International Conference on Information Security Applications - 2025, - 96～108 - 共13页

摘要：The vulnerability of deep learning models to | adversarial attacks poses a significant challenge in | artificial intelligence, particularly in deepfake detection | . Adversarial training has emerged as a crucial defense | mechanism, highlighting the importance of highly

关键词： Adversarial attacks | Adversarial training | Random masking | Boosting transferability | Low-frequency

6. ARP Spoofing Mitigation for the E2 Interface in Open RAN: An xApp Approach NSTL国家科技图书文献中心

Jihye Kim | Jaehyoung Park ... - 《Information Security Applications》 - International Conference on Information Security Applications - 2025, - 31～43 - 共13页

摘要：In the 5G-Advanced and 6G era, the Open Radio | Access Network (Open RAN) will support hardware and | software interoperability between different vendors. The | O-RAN Alliance, which leads the Open RAN | initiative, has released standards addressing potential

关键词： Open RAN | E2 interface | XApp | MitM

7. Fuzzing JavaScript Engines with Diversified Mutation Strategies NSTL国家科技图书文献中心

Cheng-Han Shie | Pin-Huang Fang ... - 《Information Security Applications》 - International Conference on Information Security Applications - 2025, - 243～254 - 共12页

摘要：Current fuzzers for JavaScript (JS) engines | often produce test cases that are syntactically | correct but semantically incorrect, hindering efficient | crash discovery. To address this issue, we propose | three mutation methods: simple mutation, state

关键词： Fuzzing | Javascript engine | Abstract syntax tree (AST) | Just-in-time (JIT) compilation

8. Field Testing and Detection of Camera Interference for Autonomous Driving NSTL国家科技图书文献中心

Ki Beom Park | Huy Kang Kim - 《Information Security Applications》 - International Conference on Information Security Applications - 2025, - 191～202 - 共12页

摘要：In recent advancements in connected and | autonomous vehicles (CAVs), automotive ethernet has emerged | as a critical technology for in-vehicle networks | (IVNs), superseding traditional protocols like the CAN | due to its superior bandwidth and data transmission

关键词： Automotive ethernet and camera interference | Intrusion detection

9. Plotting OSS-Based Supply Chain Attack Strategies and the Defense Failure NSTL国家科技图书文献中心

Arpita Dinesh Sarang | Sang-Hoon Choi ... - 《Information Security Applications》 - International Conference on Information Security Applications - 2025, - 311～323 - 共13页

摘要：The supply chain attack, which targets open | -source software, is currently the most discussed | cyberattack. This is due to the recent open-source XZ utils | and PyPI projects based attacks where the attackers | employed similar strategies. A backdoor was injected in

关键词： Supply chain attack | Linux distribution | Cyber security | Supply chain attack as a service (SCAaaS) | Open source software (OSS) security | Software bill of materials (SBOM)

10. LLM Guardrail Framework: A Novel Approach for Implementing Zero Trust Architecture NSTL国家科技图书文献中心

Bogeum Kim | Hyejin Sim ... - 《Information Security Applications》 - International Conference on Information Security Applications - 2025, - 138～148 - 共11页

摘要：This paper proposes an LLM guardrail framework | that incorporates a Zero Trust architecture to | validate and control the responses of Large Language | Model (LLM) to unethical queries. The proposed | framework applies guardrails to harmful inputs to avoid

摘要：Short-term load forecasting (STLF) is a | critical issue for managing electricity distribution | systems because its accuracy might strongly impact the | performance and security of the power system. An effective | load forecasting system, of course, can also be used

关键词： Smart grid | Deep learning | Machine learning

摘要：With the rapid development of technology | , smart devices have become indispensable tools for | people, and IoT devices are ubiquitous, playing an | important role in our daily lives. When using IoT device | applications and services, users must go through complex

关键词： Physically unclonable functions | Authentication | Authorization | Key exchange | Internet of things

摘要：Visual Basic Script (VBS)-based malicious code | exists in various forms such as document type | , executable file, and LNK file. After disguising it as a | normal file or exploiting a vulnerability to trick the | user into executing it, malicious actions are

关键词： Malware | VBS | Windows | Case analysis | MITRE ATT&CK

摘要：Generative Adversarial Networks (GANs | ) produces samples with the same probability distribution | as the given training data. However, as they | frequently train with sensitive data to generate realistic | samples, many people are concerned about the leakage of

关键词： AI security | Machine learning | Computer vision

摘要：The vulnerability of deep learning models to | adversarial attacks poses a significant challenge in | artificial intelligence, particularly in deepfake detection | . Adversarial training has emerged as a crucial defense | mechanism, highlighting the importance of highly

关键词： Adversarial attacks | Adversarial training | Random masking | Boosting transferability | Low-frequency

摘要：In the 5G-Advanced and 6G era, the Open Radio | Access Network (Open RAN) will support hardware and | software interoperability between different vendors. The | O-RAN Alliance, which leads the Open RAN | initiative, has released standards addressing potential

关键词： Open RAN | E2 interface | XApp | MitM

摘要：Current fuzzers for JavaScript (JS) engines | often produce test cases that are syntactically | correct but semantically incorrect, hindering efficient | crash discovery. To address this issue, we propose | three mutation methods: simple mutation, state

关键词： Fuzzing | Javascript engine | Abstract syntax tree (AST) | Just-in-time (JIT) compilation

摘要：In recent advancements in connected and | autonomous vehicles (CAVs), automotive ethernet has emerged | as a critical technology for in-vehicle networks | (IVNs), superseding traditional protocols like the CAN | due to its superior bandwidth and data transmission

关键词： Automotive ethernet and camera interference | Intrusion detection

摘要：The supply chain attack, which targets open | -source software, is currently the most discussed | cyberattack. This is due to the recent open-source XZ utils | and PyPI projects based attacks where the attackers | employed similar strategies. A backdoor was injected in

关键词： Supply chain attack | Linux distribution | Cyber security | Supply chain attack as a service (SCAaaS) | Open source software (OSS) security | Software bill of materials (SBOM)

摘要：This paper proposes an LLM guardrail framework | that incorporates a Zero Trust architecture to | validate and control the responses of Large Language | Model (LLM) to unethical queries. The proposed | framework applies guardrails to harmful inputs to avoid

关键词： Large language model | Guardrail | Zero trust

4008-161-200 800-990-8900

国家科技图书文献中心