Related papers: Semantic Ranking for Automated Adversarial Techniq…

Retrieval-augmented generation (RAG) systems are increasingly deployed in sensitive domains such as healthcare and law, where they rely on private, domain-specific knowledge. This capability introduces significant security risks, including…

In this paper we revisit the problem of automatically identifying hate speech in posts from social media. We approach the task using a system based on minimalistic compositional Recurrent Neural Networks (RNN). We tested our approach on the…

Adversarial transferability in black-box scenarios presents a unique challenge: while attackers can employ surrogate models to craft adversarial examples, they lack assurance on whether these examples will successfully compromise the target…

Adversarial training, which is to enhance robustness against adversarial attacks, has received much attention because it is easy to generate human-imperceptible perturbations of data to deceive a given deep neural network. In this paper, we…

As powerful Large Language Models (LLMs) are now widely used for numerous practical applications, their safety is of critical importance. While alignment techniques have significantly improved overall safety, LLMs remain vulnerable to…

Security classifiers, designed to detect malicious content in computer systems and communications, can underperform when provided with insufficient training data. In the security domain, it is often easy to find samples of the negative…

This work proposes a novel adaptation of a pretrained sequence-to-sequence model to the task of document ranking. Our approach is fundamentally different from a commonly-adopted classification-based formulation of ranking, based on…

In recent years, Reward Machines (RMs) have stood out as a simple yet effective automata-based formalism for exposing and exploiting task structure in reinforcement learning settings. Despite their relevance, little to no attention has been…

Large Language Model (LLM) based listwise ranking has shown superior performance in many passage ranking tasks. With the development of Large Reasoning Models (LRMs), many studies have demonstrated that step-by-step reasoning during…

LLM Agents are becoming central to intelligent systems. However, their deployment raises serious safety concerns. Existing defenses largely rely on "Safety Checks", which struggle to capture the complex semantic risks posed by harmful user…

Automatic writer identification is a common problem in document analysis. State-of-the-art methods typically focus on the feature extraction step with traditional or deep-learning-based techniques. In retrieval problems, re-ranking is a…

While numerous methods have been proposed as defenses against adversarial examples in question answering (QA), these techniques are often model specific, require retraining of the model, and give only marginal improvements in performance…

Neural ranking models have achieved remarkable progress and are now widely deployed in real-world applications such as Retrieval-Augmented Generation (RAG). However, like other neural architectures, they remain vulnerable to adversarial…

Insider threat is one of the most pernicious threat vectors to information and communication technologies (ICT)across the world due to the elevated level of trust and access that an insider is afforded. This type of threat can stem from…

The traditional way of sentence-level event detection involves two important subtasks: trigger identification and trigger classifications, where the identified event trigger words are used to classify event types from sentences. However,…

Text-guided image retrieval is to incorporate conditional text to better capture users' intent. Traditionally, the existing methods focus on minimizing the embedding distances between the source inputs and the targeted image, using the…

To enhance the efficiency of incident response triage operations, it is not cost-effective to defend all systems equally in a complex cyber environment. Instead, prioritizing the defense of critical functionality and the most vulnerable…

Standard accuracy metrics indicate that reading comprehension systems are making rapid progress, but the extent to which these systems truly understand language remains unclear. To reward systems with real language understanding abilities,…

In a number of information retrieval applications (e.g., patent search, literature review, due diligence, etc.), preventing false negatives is more important than preventing false positives. However, approaches designed to reduce review…

As automatic speech recognition (ASR) systems are now being widely deployed in the wild, the increasing threat of adversarial attacks raises serious questions about the security and reliability of using such systems. On the other hand,…