Related papers: Archiving Deferred Representations Using a Two-Tie…
Retrieval-Augmented Generation (RAG) mitigates LLM hallucinations but introduces a critical vulnerability: corpus integrity. We present SilentRetrieval, a two-stage data poisoning attack that hijacks RAG systems through adversarially…
Given a text, rank and select queries return the number of occurrences of a character up to a position (rank) or the position of a character with a given rank (select). These queries have applications in, e.g., compression, computational…
In e-commerce, head queries account for the vast majority of gross merchandise sales and improvements to head queries are highly impactful to the business. While most supervised approaches to search perform better in head queries vs. tail…
We present a new benchmark for evaluating Deep Search--a realistic and complex form of retrieval-augmented generation (RAG) that requires source-aware, multi-hop reasoning over diverse, sparsed, but related sources. These include documents,…
In this paper we present the results of a study into the persistence and availability of web resources referenced from papers in scholarly repositories. Two repositories with different characteristics, arXiv and the UNT digital library, are…
Federated sequential recommendation (FedSeqRec) has gained growing attention due to its ability to protect user privacy. Unfortunately, the performance of FedSeqRec is still unsatisfactory because the models used in FedSeqRec have to be…
The emergence of Linked Data on the WWW has spawned research interest in an online execution of declarative queries over this data. A particularly interesting approach is traversal-based query execution which fetches data by traversing data…
Web Application Firewalls (WAFs) have been introduced as essential and popular security gates that inspect incoming HTTP traffic to filter out malicious requests and provide defenses against a diverse array of web-based threats. Evading…
Website fingerprinting (WF) attacks identify the websites visited over anonymized connections by analyzing patterns in network traffic flows, such as packet sizes, directions, or interval times using a machine learning classifier. Previous…
Multimodal creative assistants decompose user goals and route tasks to subagents for layout, styling, retrieval, and generation. Retrieval quality is pivotal, yet failures can arise at several stages: understanding user intent, choosing…
Iterative graph algorithms often compute intermediate values and update them as computation progresses. Updated output values are used as inputs for computations in current or subsequent iterations; hence the number of iterations required…
Automated agentic workflow design currently relies on per-task iterative search, which is computationally prohibitive and fails to reuse structural knowledge across tasks. We observe that optimized workflows converge to a small family of…
Cross-modality interaction is a critical component in Text-Video Retrieval (TVR), yet there has been little examination of how different influencing factors for computing interaction affect performance. This paper first studies the…
In this paper, we address the problem of privacy-preserving federated neural network training with $N$ users. We present Hercules, an efficient and high-precision training framework that can tolerate collusion of up to $N-1$ users. Hercules…
Information retrieval (IR) in dynamic data streams is a crucial task, as shifts in data distribution degrade the performance of AI-powered IR systems. To mitigate this issue, memory-based continual learning has been widely adopted for IR.…
Website fingerprinting (WF) attacks infer the websites visited by users from encrypted traffic in anonymous networks such as Tor. Existing deep learning methods achieve high accuracy under the single-tab assumption but degrade substantially…
Cyber threat intelligence (CTI) analysts must answer complex questions over large collections of narrative security reports. Retrieval-augmented generation (RAG) systems help language models access external knowledge, but traditional vector…
The searching procedure of neural architecture search (NAS) is notoriously time consuming and cost prohibitive.To make the search space continuous, most existing gradient-based NAS methods relax the categorical choice of a particular…
Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over 72-hour operation windows due to four compounding failure modes in existing flat-file…
Lifelong user behavior sequences are crucial for capturing user interests and predicting user responses in modern recommendation systems. A two-stage paradigm is typically adopted to handle these long sequences: a subset of relevant…