arXiv subjects

Dan Ristea

Publications and source records attributed to Dan Ristea.

6 recordsLinked to original sources

arXiv2026

Referential Security as a New Paradigm for AI Evaluations

Security evaluations inherently depend on stable identifiers. Any finding, audit, or regulatory decision must remain attached to the specific artifact it pertains to. Continuously updated artificial intelligence systems violate this core assumption, with public model designations remaining static while underlying weights, prompts, retrieval mechanisms, misuse classifiers, inference settings, and serving infrastructures undergo unannounced modifications. Consequently, current evaluations frequently apply to superficial labels rather than identifiable and distinct systems. To resolve this, we propose referential security as a new paradigm for AI evaluation. The fundamental security question extends beyond whether a model is safe to whether subsequent parties can conclusively determine which system a specific safety claim addressed. This approach reframes model identity as an empirically verifiable property and separates referential stability from the substantive security claims it conditions. This framework brings tractability to three critical workflows that current practices handle poorly. Specifically, it enables reproducible evaluation, longitudinal audit validity, and cross-provider equivalence. By grounding these evaluations in verifiable artifacts, our approach ensures that safety audits and regulatory findings maintain their empirical utility across the operational lifecycle of dynamic systems.

cs.CR↗

arXiv2026

Are we collaborative yet? A Usability Perspective on Mixnet Latency for Real-Time Applications

Mixnet networks deliberately induce additional latency to communications to provide anonymity. Recent developments have allowed mixnets to reduce their latency from hours to seconds while maintaining the same level of anonymity. As a result, real-time communications are now possible on mixnets. There has been limited research on how users tolerate different levels of delay, and it is unclear what latency levels mixnet operators should choose. Previous studies about latency do not apply to these 'mid-latency' mixnet scenarios. Our paper contributes the first measurement of users' tolerance to real-time applications under mixnet delay. We design a text-based collaborative quiz system to test user response to latency where participants complete a set of question tasks in collaboration with a simulated second user. Different levels of latency are added, analogous to a modern mixnet system. We show that average delay parameters of 1s and 4s maintain usability, a mean delay of 7s shows some difficulty and a mean delay of 10s is detrimental to user experience. Using these delay parameters, mixnet operators can ensure that most types of real-time communication applications are usable. Mixnets thus can balance usability and anonymity without compromising either.

cs.HC↗

arXiv2025

One Pic is All it Takes: Poisoning Visual Document Retrieval Augmented Generation with a Single Image

Retrieval-augmented generation (RAG) is instrumental for inhibiting hallucinations in large language models (LLMs) through the use of a factual knowledge base (KB). Although PDF documents are prominent sources of knowledge, text-based RAG pipelines are ineffective at capturing their rich multi-modal information. In contrast, visual document RAG (VD-RAG) uses screenshots of document pages as the KB, which has been shown to achieve state-of-the-art results. However, by introducing the image modality, VD-RAG introduces new attack vectors for adversaries to disrupt the system by injecting malicious documents into the KB. In this paper, we demonstrate the vulnerability of VD-RAG to poisoning attacks targeting both retrieval and generation. We define two attack objectives and demonstrate that both can be realized by injecting only a single adversarial image into the KB. Firstly, we introduce a targeted attack against one or a group of queries with the goal of spreading targeted disinformation. Secondly, we present a universal attack that, for any potential user query, influences the response to cause a denial-of-service in the VD-RAG system. We investigate the two attack objectives under both white-box and black-box assumptions, employing a multi-objective gradient-based optimization approach as well as prompting state-of-the-art generative models. Using two visual document datasets, a diverse set of state-of-the-art retrievers (embedding models) and generators (vision language models), we show VD-RAG is vulnerable to poisoning attacks in both the targeted and universal settings, yet demonstrating robustness to black-box attacks in the universal setting.

cs.CL↗

arXiv2024

Direction for Detection: A Survey of Automated Vulnerability Detection and all of its Pain Points

Security vulnerabilities in software can have severe consequences; however, manual vulnerability detection is costly and does not scale, especially as agentic coding frameworks increase the rate of code production. Over the last decade, a large body of research has applied machine learning machine learning to automate vulnerability detection (ML4AVD), yet self-reported performance on the most popular datasets shows no clear upward trend. The ML4AVD research community has identified several flaws in problem formulations, datasets, and metrics, but these are discussed in isolation, leaving the overarching problems that generate and reinforce these flaws unaddressed. We first systematize the field through a survey of 87 influential works based on their problem formulation, input and detection granularity, target programming languages, evaluation metrics, datasets, and detection approach. Drawing on this corpus and prior empirical work, we identify twelve pain points spanning the ML4AVD pipeline and show that they are self-reinforcing and causally inter-meshed: feedback loops between datasets, formulations, baselines, and metrics perpetuate each other and explain the field's persistent concentration on binary classification of C/C++ vulnerabilities at the function level. Thus, the field optimizes for a narrow and artificial problem that omits vulnerability type prediction, broader language support, and separation of input from detection granularity. We pair each pain point with concrete recommendations to break these loops. Finally, we use AIxCC as a case study to assess how well a recent high-profile effort aligns with these recommendations and reflect on the relevance of ML4AVD in the era of agentic AI.

cs.SE↗

arXiv2024

HonestCyberEval: An AI Cyber Risk Benchmark for Automated Software Exploitation

We introduce HonestCyberEval, a new benchmark for assessing AI models' capabilities and risks in automated software exploitation, focusing on their ability to detect and exploit vulnerabilities in real-world software systems. Our evaluation leverages the Nginx web server repository augmented with synthetic vulnerabilities. We assess several leading language models, including OpenAI's GPT-4.5, o3-mini, o1 and o1-mini, Anthropic's Claude-3-7-sonnet-20250219, Claude-3.5-sonnet-20241022 and Claude-3.5-sonnet-20240620, Google DeepMind's Gemini-1.5-pro, and OpenAI's earlier GPT-4o model. Our findings reveal that these models vary significantly in their success rates and efficiency, with o1-preview achieving the highest success rate (92.85\%) and o3-mini and Claude-3.7-sonnet-20250219 providing cost-effective but less successful alternatives. This risk evaluation establishes a foundation for systematically evaluating the AI cyber risk in realistic cyber offence operations.

cs.CR↗

arXiv2023

Scalable Time-Lock Puzzle

Time-Lock Puzzles (TLPs) enable a client to lock a message such that a server can unlock it only after a specified time. They have diverse applications, such as scheduled payments, secret sharing, and zero-knowledge proofs. In this work, we present a scalable TLP designed for real-world scenarios involving a large number of puzzles, where clients or servers may lack the computational resources to handle high workloads. Our contributions are both theoretical and practical. From a theoretical standpoint, we formally define the concept of a Delegated Time-Lock Puzzle (D-TLP), establish its fundamental properties, and introduce an upper bound for TLPs, addressing a previously overlooked aspect. From a practical standpoint, we introduce the Efficient Delegated Time-Lock Puzzle (ED-TLP) protocol, which implements the D-TLP concept. This protocol enables both the client and server to securely outsource their resource-intensive tasks to third-party helpers. It enables real-time verification of solutions and guarantees their delivery within predefined time limits by integrating an upper bound and a fair payment algorithm. ED-TLP allows combining puzzles from different clients, enabling a solver to process them sequentially, significantly reducing computational resources, especially for a large number of puzzles or clients. ED-TLP is the first protocol of its kind. We have implemented ED-TLP and conducted a comprehensive analysis of its performance for up to 10,000 puzzles. The results highlight its significant efficiency in TLP applications, demonstrating that ED-TLP securely delegates 99% of the client's workload and 100% of the server's workload with minimal overhead.

cs.CR↗