Dense Contexts Are Hard Contexts: Lexical Density Limits Effective Context in LLMs

Input length and the position of relevant information are widely cited as the primary causes of degraded LLM long-context performance. Here, we study lexical density -- the rate at which a context introduces distinct information -- as a third, largely overlooked factor that systematically reduces the effective context window of LLMs. We quantify the impact of lexical density on open-weight LLMs (9B-685B) using three "find-the-needle" style benchmarks with identical length (~12k tokens) and controlled needle position, but increasing density of information. We observe a sharp performance collapse in higher-density benchmarks: models that are near-perfect in sparse contexts drop below 60% retrieval score on denser ones. To rule out task-type confounds, we vary and control the density within each benchmark while keeping all other properties unchanged. Reducing density generally restores performance, especially in the high-density regimes where degradation appears. These results show that effective context capacity is a function of lexical density, with direct implications for real-world LLM systems operating on compact, information-rich inputs.

Towards Agentic Honeynet Configuration

Honeypots are deception systems that emulate vulnerable services to collect threat intelligence. While deploying many honeypots increases the opportunity to observe attacker behaviour, in practise network and computational resources limit the number of honeypots that can be exposed. Hence, practitioners must select the assets to deploy, a decision that is typically made statically despite attackers' tactics evolving over time. This work investigates an AI-driven agentic architecture that autonomously manages honeypot exposure in response to ongoing attacks. The proposed agent analyses Intrusion Detection System (IDS) alerts and network state to infer the progression of the attack, identify compromised assets, and predict likely attacker targets. Based on this assessment, the agent dynamically reconfigures the system to maintain attacker engagement while minimizing unnecessary exposure. The approach is evaluated in a simulated environment where attackers execute Proof-of-Concept exploits for known CVEs. Preliminary results indicate that the agent can effectively infer the intent of the attacker and improve the efficiency of exposure under resource constraints

Mixture of Concept Bottleneck Experts

Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts. However, existing CBMs typically fix their task predictor to a single linear or Boolean expression, limiting both predictive accuracy and adaptability to diverse user needs. We propose Mixture of Concept Bottleneck Experts (M-CBEs), a framework that generalizes existing CBMs along two dimensions: the number of experts and the functional form of each expert, exposing an underexplored region of the design space. We investigate this region by instantiating two novel models: Linear M-CBE, which learns a finite set of linear expressions, and Symbolic M-CBE, which leverages symbolic regression to discover expert functions from data under user-specified operator vocabularies. Empirical evaluation demonstrates that varying the mixture size and functional form provides a robust framework for navigating the accuracy-interpretability trade-off, adapting to different user and task needs.

V-CEM: Bridging Performance and Intervenability in Concept-based Models

Concept-based eXplainable AI (C-XAI) is a rapidly growing research field that enhances AI model interpretability by leveraging intermediate, human-understandable concepts. This approach not only enhances model transparency but also enables human intervention, allowing users to interact with these concepts to refine and improve the model's performance. Concept Bottleneck Models (CBMs) explicitly predict concepts before making final decisions, enabling interventions to correct misclassified concepts. While CBMs remain effective in Out-Of-Distribution (OOD) settings with intervention, they struggle to match the performance of black-box models. Concept Embedding Models (CEMs) address this by learning concept embeddings from both concept predictions and input data, enhancing In-Distribution (ID) accuracy but reducing the effectiveness of interventions, especially in OOD scenarios. In this work, we propose the Variational Concept Embedding Model (V-CEM), which leverages variational inference to improve intervention responsiveness in CEMs. We evaluated our model on various textual and visual datasets in terms of ID performance, intervention responsiveness in both ID and OOD settings, and Concept Representation Cohesiveness (CRC), a metric we propose to assess the quality of the concept embedding representations. The results demonstrate that V-CEM retains CEM-level ID performance while achieving intervention effectiveness similar to CBM in OOD settings, effectively reducing the gap between interpretability (intervention) and generalization (performance).

Self-supervised Interpretable Concept-based Models for Text Classification

Despite their success, Large-Language Models (LLMs) still face criticism as their lack of interpretability limits their controllability and reliability. Traditional post-hoc interpretation methods, based on attention and gradient-based analysis, offer limited insight into the model's decision-making processes. In the image field, Concept-based models have emerged as explainable-by-design architectures, employing human-interpretable features as intermediate representations. However, these methods have not been yet adapted to textual data, mainly because they require expensive concept annotations, which are impractical for real-world text data. This paper addresses this challenge by proposing a self-supervised Interpretable Concept Embedding Models (ICEMs). We leverage the generalization abilities of LLMs to predict the concepts labels in a self-supervised way, while we deliver the final predictions with an interpretable function. The results of our experiments show that ICEMs can be trained in a self-supervised way achieving similar performance to fully supervised concept-based models and end-to-end black-box ones. Additionally, we show that our models are (i) interpretable, offering meaningful logical explanations for their predictions; (ii) interactable, allowing humans to modify intermediate predictions through concept interventions; and (iii) controllable, guiding the LLMs' decoding process to follow a required decision-making path.

LogPrécis: Unleashing Language Models for Automated Shell Log Analysis

The collection of security-related logs holds the key to understanding attack behaviors and diagnosing vulnerabilities. Still, their analysis remains a daunting challenge. Recently, Language Models (LMs) have demonstrated unmatched potential in understanding natural and programming languages. The question arises whether and how LMs could be also useful for security experts since their logs contain intrinsically confused and obfuscated information. In this paper, we systematically study how to benefit from the state-of-the-art in LM to automatically analyze text-like Unix shell attack logs. We present a thorough design methodology that leads to LogPr\'ecis. It receives as input raw shell sessions and automatically identifies and assigns the attacker tactic to each portion of the session, i.e., unveiling the sequence of the attacker's goals. We demonstrate LogPr\'ecis capability to support the analysis of two large datasets containing about 400,000 unique Unix shell attacks. LogPr\'ecis reduces them into about 3,000 fingerprints, each grouping sessions with the same sequence of tactics. The abstraction it provides lets the analyst better understand attacks, identify fingerprints, detect novelty, link similar attacks, and track families and mutations. Overall, LogPr\'ecis, released as open source, paves the way for better and more responsive defense against cyberattacks.