10 citations · 12 across the 9 of their papers we have counts for
9 papers
Graphs Don't Stay Secret: Practical Subgraph Reconstruction Attacks on Defended Graph RAG
Minkyoo Song, Jaehan Kim, Myungchul Kang +3
Graph-based retrieval-augmented generation (Graph RAG) is increasingly deployed to support LLM applications by augmenting user queries with structured knowledge retrieved from a kn…
Heimdallr: Fingerprinting SD-WAN Control-Plane Architecture via Encrypted Control Traffic
Minjae Seo, Jaehan Kim, Eduard Marin +5
Software-defined wide area network (SD-WAN) has emerged as a new paradigm for steering a large-scale network flexibly by adopting distributed software-defined network (SDN) control…
PassREfinder-FL: Privacy-Preserving Credential Stuffing Risk Prediction via Graph-Based Federated Learning for Representing Password Reuse between Websites
Jaehan Kim, Minkyoo Song, Minjae Seo +3
Credential stuffing attacks have caused significant harm to online users who frequently reuse passwords across multiple websites. While prior research has attempted to detect users…
Defending MoE LLMs against Harmful Fine-Tuning via Safety Routing Alignment
Jaehan Kim, Minkyoo Song, Seungwon Shin +1
Recent large language models (LLMs) have increasingly adopted the Mixture-of-Experts (MoE) architecture for efficiency. MoE-based LLMs heavily depend on a superficial safety mechan…
MUFFLER: Secure Tor Traffic Obfuscation with Dynamic Connection Shuffling and Splitting
Minjae Seo, Myoungsung You, Jaehan Kim +3
Tor, a widely utilized privacy network, enables anonymous communication but is vulnerable to flow correlation attacks that deanonymize users by correlating traffic patterns from To…
EO-VLM: VLM-Guided Energy Overload Attacks on Vision Models
Minjae Seo, Myoungsung You, Junhee Lee +4
Vision models are increasingly deployed in critical applications such as autonomous driving and CCTV monitoring, yet they remain susceptible to resource-consuming attacks. In this…
Covering Cracks in Content Moderation: Delexicalized Distant Supervision for Illicit Drug Jargon Detection
Minkyoo Song, Eugene Jang, Jaehan Kim +1
In light of rising drug-related concerns and the increasing role of social media, sales and discussions of illicit drugs have become commonplace online. Social media platforms host…
Obliviate: Neutralizing Task-agnostic Backdoors within the Parameter-efficient Fine-tuning Paradigm
Jaehan Kim, Minkyoo Song, Seung Ho Na +1
Parameter-efficient fine-tuning (PEFT) has become a key training strategy for large language models. However, its reliance on fewer trainable parameters poses security risks, such…
Claim-Guided Textual Backdoor Attack for Practical Applications
Minkyoo Song, Hanna Kim, Jaehan Kim +2
Recent advances in natural language processing and the increased use of large language models have exposed new security vulnerabilities, such as backdoor attacks. Previous backdoor…