Papers Computer Security
“Computer Security” 태그가 달린 논문 70편 · 필터 해제
Agent Safety Should Be a Runtime Contract
The dominant paradigm treats AI safety as a property to be instilled during model training via RLHF, DPO, or Constitutional AI. We argue this is structurally insufficient for autonomous agents that execute code, mutate f…
Computer SecurityREBENCH: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names (Extended Version)
Large Language Models (LLMs) have achieved remarkable progress in recent years, driving their adoption across a wide range of domains, including computer security. In reverse engineering, LLMs are increasingly applied to…
Computer SecurityEvasive Intelligence: Lessons from Malware Analysis for Evaluating AI Agents
Artificial intelligence (AI) systems are increasingly adopted as tool-using agents that can plan, observe their environment, and take actions over extended time periods. This evolution challenges current evaluation pract…
Computer SecurityCommandSans: Securing AI Agents with Surgical Precision Prompt Sanitization
The increasing adoption of LLM agents with access to numerous tools and sensitive data significantly widens the attack surface for indirect prompt injections. Due to the context-dependent nature of attacks, however, curr…
Computer SecurityEmergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs
We present a surprising result regarding LLMs and alignment. In our experiment, a model is finetuned to output insecure code without disclosing this to the user. The resulting model acts misaligned on a broad range of pr…
Computer SecurityThe Pitfalls of "Security by Obscurity" And What They Mean for Transparent AI
Calls for transparency in AI systems are growing in number and urgency from diverse stakeholders ranging from regulators to researchers to users (with a comparative absence of companies developing AI). Notions of transpa…
Computer SecurityCySecBench: Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models
Numerous studies have investigated methods for jailbreaking Large Language Models (LLMs) to generate harmful content. Typically, these methods are evaluated using datasets of malicious prompts designed to bypass security…
BenchmarkingComputer SecurityDataset GenerationLarge Language Model+1Expectation vs. Reality: Towards Verification of Psychological Games
Game theory provides an effective way to model strategic interactions among rational agents. In the context of formal verification, these ideas can be used to produce guarantees on the correctness of multi-agent systems,…
Autonomous DrivingComputer SecurityTDDBench: A Benchmark for Training data detection
Training Data Detection (TDD) is a task aimed at determining whether a specific data instance is used to train a machine learning model. In the computer security literature, TDD is also referred to as Membership Inferenc…
BenchmarkingComputational EfficiencyComputer SecurityInference Attack+1Revisiting Static Feature-Based Android Malware Detection
The increasing reliance on machine learning (ML) in computer security, particularly for malware classification, has driven significant advancements. However, the replicability and reproducibility of these results are oft…
Android Malware DetectionComputer SecurityContinual LearningMalware Analysis+2Malicious Internet Entity Detection Using Local Graph Inference
Detection of malicious behavior in a large network is a challenging problem for machine learning in computer security, since it requires a model with high expressive power and scalable inference. Existing solutions strug…
Computer SecurityTransforming Computer Security and Public Trust Through the Exploration of Fine-Tuning Large Language Models
Large language models (LLMs) have revolutionized how we interact with machines. However, this technological advancement has been paralleled by the emergence of "Mallas," malicious services operating underground that expl…
Computer SecurityA Roadmap for Multilingual, Multimodal Domain Independent Deception Detection
Deception, a prevalent aspect of human communication, has undergone a significant transformation in the digital age. With the globalization of online interactions, individuals are communicating in multiple languages and …
Computer SecurityDeception DetectionOnline Clustering of Known and Emerging Malware Families
Malware attacks have become significantly more frequent and sophisticated in recent years. Therefore, malware detection and classification are critical components of information security. Due to the large amount of malwa…
ClusteringComputer SecurityMalware DetectionOnline ClusteringFrom Clicks to Security: Investigating Continuous Authentication via Mouse Dynamics
In the realm of computer security, the importance of efficient and reliable user authentication methods has become increasingly critical. This paper examines the potential of mouse movement dynamics as a consistent metri…
Computer SecurityAutoAttacker: A Large Language Model Guided System to Implement Automatic Cyber-attacks
Large language models (LLMs) have demonstrated impressive results on natural language tasks, and security researchers are beginning to employ them in both offensive and defensive systems. In cyber-security, there have be…
Computer SecurityLanguage ModelingLanguage ModellingLarge Language ModelDetecting Face Synthesis Using a Concealed Fusion Model
Face image synthesis is gaining more attention in computer security due to concerns about its potential negative impacts, including those related to fake biometrics. Hence, building models that can detect the synthesized…
Computer SecurityFace GenerationImage Generationmodel+1SecQA: A Concise Question-Answering Dataset for Evaluating Large Language Models in Computer Security
In this paper, we introduce SecQA, a novel dataset tailored for evaluating the performance of Large Language Models (LLMs) in the domain of computer security. Utilizing multiple-choice questions generated by GPT-4 based …
Computer SecurityMultiple-choiceQuestion AnsweringAnomaly Detection of Command Shell Sessions based on DistilBERT: Unsupervised and Supervised Approaches
Anomaly detection in command shell sessions is a critical aspect of computer security. Recent advances in deep learning and natural language processing, particularly transformer-based models, have shown great promise for…
Anomaly DetectionComputer SecurityLLM Censorship: A Machine Learning Challenge or a Computer Security Problem?
Large language models (LLMs) have exhibited impressive capabilities in comprehending complex instructions. However, their blind adherence to provided instructions has led to concerns regarding risks of malicious use. Exi…
Computer SecurityInstruction Following