paper-with-me

Papers Computer Security

“Computer Security” 태그가 달린 논문 70편 · 필터 해제

A LLM Assisted Exploitation of AI-Guardian

2023-07-20 · Nicholas Carlini

Large language models (LLMs) are now highly capable at a diverse range of tasks. This paper studies whether or not GPT-4, one such LLM, is capable of assisting researchers in the field of adversarial machine learning. As…

Computer SecurityLanguage ModelingLanguage Modelling

Covert Communication Based on the Poisoning Attack in Federated Learning

2023-06-02 · Junchuan Liang, Rong Wang

Covert communication has become an important area of research in computer security. It involves hiding specific information on a carrier for message transmission and is often used to transmit private data, military secre…

Computer SecurityFederated Learning

Understand Waiting Time in Transaction Fee Mechanism: An Interdisciplinary Perspective

2023-05-04 · Luyao Zhang, Fan Zhang

Blockchain enables peer-to-peer transactions in cyberspace without a trusted third party. The rapid growth of Ethereum and smart contract blockchains generally calls for well-designed Transaction Fee Mechanisms (TFMs) to…

Causal InferenceComputer SecurityTime SeriesTime Series Analysis

Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection

2023-02-23 · Kai Greshake, Sahar Abdelnabi, Shailesh Mishra, Christoph Endres 외

Large Language Models (LLMs) are increasingly being integrated into various applications. The functionalities of recent LLMs can be flexibly modulated via natural language prompts. This renders them susceptible to target…

Code CompletionComputer SecurityInstruction FollowingRetrieval

Exploiting Programmatic Behavior of LLMs: Dual-Use Through Standard Security Attacks

2023-02-11 · Daniel Kang, Xuechen Li, Ion Stoica, Carlos Guestrin 외

Recent advances in instruction-following large language models (LLMs) have led to dramatic improvements in a range of NLP tasks. Unfortunately, we find that the same improved capabilities amplify the dual-use risks for m…

Computer SecurityInstruction Following

Defensive ML: Defending Architectural Side-channels with Adversarial Obfuscation

2023-02-03 · Hyoungwook Nam, Raghavendra Pradyumna Pothukuchi, Bo Li, Nam Sung Kim 외

Side-channel attacks that use machine learning (ML) for signal analysis have become prominent threats to computer security, as ML models easily find patterns in signals. To address this problem, this paper explores using…

Computer Security

Indexing AI Risks with Incidents, Issues, and Variants

2022-11-18 · Sean McGregor, Kevin Paeth, Khoa Lam

Two years after publicly launching the AI Incident Database (AIID) as a collection of harms or near harms produced by AI in the world, a backlog of "issues" that do not meet its incident ingestion criteria have accumulat…

Computer Security

Pre-Training Representations of Binary Code Using Contrastive Learning

2022-10-11 · Yifan Zhang, Chen Huang, Yueke Zhang, Kevin Cao 외

Binary code analysis and comprehension is critical to applications in reverse engineering and computer security tasks where source code is not available. Unfortunately, unlike source code, binary code lacks semantics and…

Code SummarizationComputer SecurityContrastive LearningRepresentation Learning+1

Why So Toxic? Measuring and Triggering Toxic Behavior in Open-Domain Chatbots

2022-09-07 · Wai Man Si, Michael Backes, Jeremy Blackburn, Emiliano De Cristofaro 외

Chatbots are used in many applications, e.g., automated agents, smart home assistants, interactive characters in online games, etc. Therefore, it is crucial to ensure they do not behave in undesired manners, providing of…

ChatbotComputer Security

SoK: Explainable Machine Learning for Computer Security Applications

2022-08-22 · Azqa Nadeem, Daniël Vos, Clinton Cao, Luca Pajola 외

Explainable Artificial Intelligence (XAI) aims to improve the transparency of machine learning (ML) pipelines. We systematize the increasingly growing (but fragmented) microcosm of studies that develop and utilize XAI me…

Computer SecurityExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)

IR-ORAM: Path Access Type Based Memory Intensity Reduction for Path-ORAM

2022-05-17 · IEEE International Symposium on High-Performance Computer Architecture (HPCA) 2022 5 · Mehrnoosh Raoufi, Youtao Zhang, Jun Yang

Path ORAM is an effective ORAM (Oblivious RAM) primitive for protecting memory access patterns. Path ORAM converts each off-chip memory request from user program to tens to hundreds of memory accesses. While several sche…

Computer Architecture and SystemsComputer SecurityPositionPrivacy Preserving

A new Sparse Auto-encoder based Framework using Grey Wolf Optimizer for Data Classification Problem

2022-01-29 · Ahmad Mozaffer Karim

One of the most important properties of deep auto-encoders (DAEs) is their capability to extract high level features from row data. Hence, especially recently, the autoencoders are preferred to be used in various classif…

Computer Security

Physical Activity Recognition by Utilising Smartphone Sensor Signals

2022-01-20 · Abdulrahman Alruban, Hind Alobaidi, Nathan Clarke' Fudong Li

Human physical motion activity identification has many potential applications in various fields, such as medical diagnosis, military sensing, sports analysis, and human-computer security interaction. With the recent adva…

Activity RecognitionComputer SecurityMedical Diagnosis

Scaling Language Models: Methods, Analysis & Insights from Training Gopher

2021-12-08 · NA 2021 12 · Jack W. Rae, Sebastian Borgeaud, Trevor Cai, Katie Millican 외

Language modelling provides a step towards intelligent communication systems by harnessing large repositories of written human knowledge to better predict and understand the world. In this paper, we present an analysis o…

Abstract AlgebraAnachronismsAnalogical SimilarityAnalytic Entailment+143

CVSS-BERT: Explainable Natural Language Processing to Determine the Severity of a Computer Security Vulnerability from its Description

2021-11-16 · Mustafizur Shahid, Hervé Debar

When a new computer security vulnerability is publicly disclosed, only a textual description of it is available. Cybersecurity experts later provide an analysis of the severity of the vulnerability using the Common Vulne…

Computer Security

Generating Cyber Threat Intelligence to Discover Potential Security Threats Using Classification and Topic Modeling

2021-08-16 · Md Imran Hossen, Ashraful Islam, Farzana Anowar, Eshtiak Ahmed 외

Due to the variety of cyber-attacks or threats, the cybersecurity community enhances the traditional security control mechanisms to an advanced level so that automated tools can encounter potential security threats. Very…

Computer Security

Parallel Algorithms for Densest Subgraph Discovery Using Shared Memory Model

2021-02-27 · B. D. M. De Zoysa, Y. A. M. M. A. Ali, M. D. I. Maduranga, Indika Perera 외

The problem of finding dense components of a graph is a widely explored area in data analysis, with diverse applications in fields and branches of study including community mining, spam detection, computer security and b…

Computer SecuritySpam detection

Cyber Risk in Health Facilities: A Systematic Literature Review

2021-02-08 · Alberto Sardi, Alessandro Rizzi, Enrico Sorano, Anna Guerrieri

The current world challenges include issues such as infectious disease pandemics, environmental health risks, food safety, and crime prevention. Through this article, a special emphasis is given to one of the main challe…

Computer SecurityManagementSystematic Literature Review

Fragments Expert A Graphical User Interface MATLAB Toolbox for Classification of File Fragments

2020-12-23 · Concurrency and Computation Practice and Experience 2020 12 · Mehdi Teimouri, Zahra Seyedghorban, Fatemeh Amirjani

The classification of file fragments of various file formats is an essential task in various applications such as firewalls, intrusion detection systems, anti-viruses, web content filtering, and digital forensics. Howeve…

ClassificationComputer SecurityFile Type IdentificationIntrusion Detection

CodeCMR: Cross-Modal Retrieval For Function-Level Binary Source Code Matching

2020-12-01 · NeurIPS 2020 12 · Zeping Yu, Wenxin Zheng, Jiaqi Wang, Qiyi Tang 외

Binary source code matching, especially on function-level, has a critical role in the field of computer security. Given binary code only, finding the corresponding source code improves the accuracy and efficiency in reve…

Computer SecurityCross-Modal RetrievalFeature EngineeringGraph Neural Network+1
← 이전 21–40 / 70 다음 →