arXiv subjects

Berkay Celik

Publications and source records attributed to Berkay Celik.

5 recordsLinked to original sources

arXiv2026

Reveree: Diagnosing LLM Reverse-Engineering Agents

Reverse engineering (RE) is critical to security tasks such as malware analysis and vulnerability discovery, and large language model (LLM) agents are increasingly able to perform it autonomously. Capture-the-flag (CTF) RE challenges have become the standard proxy for measuring this capability, but evaluation rests on a single criterion: whether the agent captures the flag. This solve rate reveals neither where in the RE process an agent fails nor whether a success reflects analysis of the binary or recall of a public solution. In this paper, we propose Reveree, a diagnostic framework that scores an LLM RE agent's trajectory at three tiers: solve rate, milestone progress through an eight-stage RE schema, and a behavioral profile of its actions. Comprehension stages are scored by an outcome-blinded LLM judge validated against a human expert; all other stages are verified deterministically. Using Reveree, we evaluate nine frontier models and four prompting strategies on 88 picoCTF and NYU-CTF challenges. We find that the base model dominates performance, whereas prompting strategy is a secondary, model-dependent effect. Surprisingly, larger, newer, or costlier models are not reliably stronger. We also find that failures concentrate at the comprehension stages of the RE process, and that extra budget, persistence, or reasoning effort rescues few of them, pointing to a competence limit rather than a resource limit. Regarding memorization, while models reproduce picoCTF flags from challenge descriptions alone, NYU-CTF shows minimal measurable recall, and most solves survive surface perturbation, indicating that genuine analysis coexists with memorization. We release Reveree to the community.

cs.CR↗

arXiv2026

D-LiFT: Improving LLM-based Decompiler Backend via Code Quality-driven Fine-tuning

As one of the key tools in many security tasks, decompilers reconstruct human-readable source code from binaries. Yet, despite recent advances, their outputs often suffer from syntactic and semantic errors and remain difficult to read. Recently, with the advent of large language models (LLMs), researchers began to explore the potential of LLMs to refine decompiler output. Nevertheless, our study of these approaches reveals their problems, such as introducing new errors and relying on unreliable accuracy validation. In this paper, we present D-LIFT, an enhanced decompiler-LLM pipeline with a fine-tuned LLM using code quality-aware reinforcement learning. Unlike prior work that overlooks preserving accuracy, D-LIFT adheres to a key principle for enhancing the quality of decompiled code: preserving accuracy while improving readability. Central to D-LIFT, we propose D-Score, an integrated code quality assessment system to score the decompiled source code from multiple aspects, and use it to guide reinforcement learning fine-tuning and to select the best output during inference. In line with our principle, D-Score assigns low scores to any inaccurate output and only awards higher scores for readability to code that passes the accuracy check. Our implementation, based on Ghidra and a range of LLMs, demonstrates significant improvements for the accurate decompiled code from the coreutils and util-linux projects. Compared to baseline LLMs without D-Score-driven fine-tuning, our trained LLMs produce 55.3% more improved decompiled functions, as measured by D-Score. Overall, D-LIFT improves the quality of 68.2% of all the functions produced by the native decompiler.

cs.CR↗

arXiv2021

Unifying Distillation with Personalization in Federated Learning

Federated learning (FL) is a decentralized privacy-preserving learning technique in which clients learn a joint collaborative model through a central aggregator without sharing their data. In this setting, all clients learn a single common predictor (FedAvg), which does not generalize well on each client's local data due to the statistical data heterogeneity among clients. In this paper, we address this problem with PersFL, a discrete two-stage personalized learning algorithm. In the first stage, PersFL finds the optimal teacher model of each client during the FL training phase. In the second stage, PersFL distills the useful knowledge from optimal teachers into each user's local model. The teacher model provides each client with some rich, high-level representation that a client can easily adapt to its local model, which overcomes the statistical heterogeneity present at different clients. We evaluate PersFL on CIFAR-10 and MNIST datasets using three data-splitting strategies to control the diversity between clients' data distributions. We empirically show that PersFL outperforms FedAvg and three state-of-the-art personalization methods, pFedMe, Per-FedAvg, and FedPer on majority data-splits with minimal communication cost. Further, we study the performance of PersFL on different distillation objectives, how this performance is affected by the equitable notion of fairness among clients, and the number of required communication rounds. PersFL code is available at https://tinyurl.com/hdh5zhxs for public use and validation.

cs.LG↗

arXiv2020

IoTRepair: Systematically Addressing Device Faults in Commodity IoT (Extended Paper)

IoT devices are decentralized and deployed in un-stable environments, which causes them to be prone to various kinds of faults, such as device failure and network disruption. Yet, current IoT platforms require programmers to handle faults manually, a complex and error-prone task. In this paper, we present IoTRepair, a fault-handling system for IoT that (1)integrates a fault identification module to track faulty devices,(2) provides a library of fault-handling functions for effectively handling different fault types, (3) provides a fault handler on top of the library for autonomous IoT fault handling, with user and developer configuration as input. Through an evaluation in a simulated lab environment and with various fault injectio nmethods,IoTRepair is compared with current fault-handling solutions. The fault handler reduces the incorrect states on average 50.01%, which corresponds to less unsafe and insecure device states. Overall, through a systematic design of an IoT fault handler, we provide users flexibility and convenience in handling complex IoT fault handling, allowing safer IoT environments.

cs.SE↗

arXiv2017

Determining Positive Cancer Rescue Mutations in p53 Based Cancers by using Artificial Intelligence

A mutation in a protein-coding gene in DNA can alter the protein structure coded by the same gene. Structurally altered proteins usually lose their functions and sometimes gain an undesirable function instead. These types of mutations and their effects can result in genetic diseases or antibiotic resistant bacteria, among other health issues. Important curing methods have been developed for detecting mutations against AIDS as well as genetic diseases. Another example is the influenza virus. The reasons why a vaccination developed to fight against influenza does not work the following year are (a) the mutation of its DNA and (b) the outbreak of the virus after it has been mutated especially if it is a virus that escaped the vaccinations target. Due to such reasons, it is highly important to know in advance the location of a potential mutation in a protein as well as the problems it might cause the medical sciences. In this study we have used artificial neural networks, which are one of the latest artificial intelligence technologies, to determine the effects of cancer mutations. The model we developed has given more successful results compared to other methods. We foresee that our model will bring a new dimension to medical research and the medical industry.

q-bio.QM↗