Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency
arXiv:2402.19366 · doi:10.1016/j.fsidi.2024.301859
Abstract
The ever-increasing workload of digital forensic labs raises concerns about law enforcement's ability to conduct both cyber-related and non-cyber-related investigations promptly. Consequently, this article explores the potential and usefulness of integrating Large Language Models (LLMs) into digital forensic investigations to address challenges such as bias, explainability, censorship, resource-intensive infrastructure, and ethical and legal considerations. A comprehensive literature review is carried out, encompassing existing digital forensic models, tools, LLMs, deep learning techniques, and the use of LLMs in investigations. The review identifies current challenges within existing digital forensic processes and explores both the obstacles and the possibilities of incorporating LLMs. In conclusion, the study states that the adoption of LLMs in digital forensics, with appropriate constraints, has the potential to improve investigation efficiency, improve traceability, and alleviate the technical and judicial barriers faced by law enforcement entities.
References in corpus (19)
- PaLM: Scaling Language Modeling with Pathways
- A Survey on Large Language Model based Autonomous Agents
- Flamingo: a Visual Language Model for Few-Shot Learning
- A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly
- Visual Instruction Tuning
- Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models
- QLoRA: Efficient Finetuning of Quantized LLMs
- Extracting Accurate Materials Data from Research Papers with Conversational Language Models and Prompt Engineering
- Reflexion: Language Agents with Verbal Reinforcement Learning
- Auditing large language models: a three-layered approach
- StarCoder: may the source be with you!
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation
- VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks
- Fine-tuning language models to find agreement among humans with diverse preferences
- CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society
- Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners
- Evaluation of LLM Chatbots for OSINT-based Cyber Threat Awareness
- Generating Images with Multimodal Language Models