arXiv subjects

Dario Pasquini

Publications and source records attributed to Dario Pasquini.

17 recordsLinked to original sources

arXiv2026

Red-Teaming the Agentic Red-Team

The use of agentic systems to perform offensive security operations has moved from a theoretical possibility to a commoditized capability. However, while the community has focused on creating more and more capable agents, less attention has been allocated to assessing the security of those systems. In this work, we present the first in-depth security analysis of the most widely used agentic systems for offensive security operations. We show that most of these tools share common design flaws that enable an active adversary to exfiltrate API keys, establish persistent footholds, and fully compromise the operator's machine, even when the agent operates inside a sandboxed container. To support our analysis, we introduce a full cyber kill chain for such agentic systems, capturing the progression from initial LLM manipulation to lateral movement, persistence, guardrail bypass, and sandbox escape. Building on our security analysis, we derive a robust architecture for agentic offensive-security tools and propose actionable, broadly applicable design principles that mitigate the disclosed attack paths at the architectural level.

cs.CR↗

arXiv2026

Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale

There is no doubt that safety alignment is an essential step in LLM training. However, conceptually it does not distinguish between various domains and the level of potential harm of a query, which creates significant complications in the fields like cyber security, where a model should not be constrained by its safety circuits to accomplish the goals of legitimate, authorized operations. In this work, we share our findings from a large scale abliteration experiment on 24 open-source LLMs and show that domain-specific abliteration is achievable with standard methodology on the example of a 1T-parameter Kimi K2. Building on recent work showing that refusal in LLMs occupies a multi-dimensional subspace within layers, we find that it is also distributed widely across layers, especially in trillion-parameter MoE architectures, and so we aim to capture the part of it that represents harmful concepts in the cybersecurity domain exclusively. We also investigate the correlation between models' features and the effect of domain-specific abliteration, identifying that the type of safety training and architecture are the most reliable predictors. Finally, we classify the models into 3 abliteration susceptibility tiers and put forward a set of conjectures as to why a particular effect from this intervention might be observed in a given model.

cs.CR↗

arXiv2025

When AIOps Become "AI Oops": Subverting LLM-driven IT Operations via Telemetry Manipulation

AI for IT Operations (AIOps) is transforming how organizations manage complex software systems by automating anomaly detection, incident diagnosis, and remediation. Modern AIOps solutions increasingly rely on autonomous LLM-based agents to interpret telemetry data and take corrective actions with minimal human intervention, promising faster response times and operational cost savings. In this work, we perform the first security analysis of AIOps solutions, showing that, once again, AI-driven automation comes with a profound security cost. We demonstrate that adversaries can manipulate system telemetry to mislead AIOps agents into taking actions that compromise the integrity of the infrastructure they manage. We introduce techniques to reliably inject telemetry data using error-inducing requests that influence agent behavior through a form of adversarial reward-hacking; plausible but incorrect system error interpretations that steer the agent's decision-making. Our attack methodology, AIOpsDoom, is fully automated--combining reconnaissance, fuzzing, and LLM-driven adversarial input generation--and operates without any prior knowledge of the target system. To counter this threat, we propose AIOpsShield, a defense mechanism that sanitizes telemetry data by exploiting its structured nature and the minimal role of user-generated content. Our experiments show that AIOpsShield reliably blocks telemetry-based attacks without affecting normal agent performance. Ultimately, this work exposes AIOps as an emerging attack vector for system compromise and underscores the urgent need for security-aware AIOps design.

cs.CR↗

arXiv2025

LLMmap: Fingerprinting For Large Language Models

We introduce LLMmap, a first-generation fingerprinting technique targeted at LLM-integrated applications. LLMmap employs an active fingerprinting approach, sending carefully crafted queries to the application and analyzing the responses to identify the specific LLM version in use. Our query selection is informed by domain expertise on how LLMs generate uniquely identifiable responses to thematically varied prompts. With as few as 8 interactions, LLMmap can accurately identify 42 different LLM versions with over 95% accuracy. More importantly, LLMmap is designed to be robust across different application layers, allowing it to identify LLM versions--whether open-source or proprietary--from various vendors, operating under various unknown system prompts, stochastic sampling hyperparameters, and even complex generation frameworks such as RAG or Chain-of-Thought. We discuss potential mitigations and demonstrate that, against resourceful adversaries, effective countermeasures may be challenging or even unrealizable.

cs.CR↗

arXiv2024

Hacking Back the AI-Hacker: Prompt Injection as a Defense Against LLM-driven Cyberattacks

Large language models (LLMs) are increasingly being harnessed to automate cyberattacks, making sophisticated exploits more accessible and scalable. In response, we propose a new defense strategy tailored to counter LLM-driven cyberattacks. We introduce Mantis, a defensive framework that exploits LLMs' susceptibility to adversarial inputs to undermine malicious operations. Upon detecting an automated cyberattack, Mantis plants carefully crafted inputs into system responses, leading the attacker's LLM to disrupt their own operations (passive defense) or even compromise the attacker's machine (active defense). By deploying purposefully vulnerable decoy services to attract the attacker and using dynamic prompt injections for the attacker's LLM, Mantis can autonomously hack back the attacker. In our experiments, Mantis consistently achieved over 95% effectiveness against automated LLM-driven attacks. To foster further research and collaboration, Mantis is available as an open-source tool: https://github.com/pasquini-dario/project_mantis

cs.CR↗

arXiv2024

Neural Exec: Learning (and Learning from) Execution Triggers for Prompt Injection Attacks

We introduce a new family of prompt injection attacks, termed Neural Exec. Unlike known attacks that rely on handcrafted strings (e.g., "Ignore previous instructions and..."), we show that it is possible to conceptualize the creation of execution triggers as a differentiable search problem and use learning-based methods to autonomously generate them. Our results demonstrate that a motivated adversary can forge triggers that are not only drastically more effective than current handcrafted ones but also exhibit inherent flexibility in shape, properties, and functionality. In this direction, we show that an attacker can design and generate Neural Execs capable of persisting through multi-stage preprocessing pipelines, such as in the case of Retrieval-Augmented Generation (RAG)-based applications. More critically, our findings show that attackers can produce triggers that deviate markedly in form and shape from any known attack, sidestepping existing blacklist-based detection and sanitation approaches.

cs.CR↗

arXiv2024

Universal Neural-Cracking-Machines: Self-Configurable Password Models from Auxiliary Data

We introduce the concept of "universal password model" -- a password model that, once pre-trained, can automatically adapt its guessing strategy based on the target system. To achieve this, the model does not need to access any plaintext passwords from the target credentials. Instead, it exploits users' auxiliary information, such as email addresses, as a proxy signal to predict the underlying password distribution. Specifically, the model uses deep learning to capture the correlation between the auxiliary data of a group of users (e.g., users of a web application) and their passwords. It then exploits those patterns to create a tailored password model for the target system at inference time. No further training steps, targeted data collection, or prior knowledge of the community's password distribution is required. Besides improving over current password strength estimation techniques and attacks, the model enables any end-user (e.g., system administrators) to autonomously generate tailored password models for their systems without the often unworkable requirements of collecting suitable training data and fitting the underlying machine learning model. Ultimately, our framework enables the democratization of well-calibrated password models to the community, addressing a major challenge in the deployment of password security solutions at scale.

cs.CR↗

arXiv2023

On the (In)security of Peer-to-Peer Decentralized Machine Learning

In this work, we carry out the first, in-depth, privacy analysis of Decentralized Learning -- a collaborative machine learning framework aimed at addressing the main limitations of federated learning. We introduce a suite of novel attacks for both passive and active decentralized adversaries. We demonstrate that, contrary to what is claimed by decentralized learning proposers, decentralized learning does not offer any security advantage over federated learning. Rather, it increases the attack surface enabling any user in the system to perform privacy attacks such as gradient inversion, and even gain full control over honest users' local model. We also show that, given the state of the art in protections, privacy-preserving configurations of decentralized learning require fully connected networks, losing any practical advantage over the federated setup and therefore completely defeating the objective of the decentralized approach.

cs.CR↗

arXiv2023

Your Email Address Holds the Key: Understanding the Connection Between Email and Password Security with Deep Learning

In this work, we investigate the effectiveness of deep-learning-based password guessing models for targeted attacks on human-chosen passwords. In recent years, service providers have increased the level of security of users'passwords. This is done by requiring more complex password generation patterns and by using computationally expensive hash functions. For the attackers this means a reduced number of available guessing attempts, which introduces the necessity to target their guess by exploiting a victim's publicly available information. In this work, we introduce a context-aware password guessing model that better capture attackers'behavior. We demonstrate that knowing a victim's email address is already critical in compromising the associated password and provide an in-depth analysis of the relationship between them. We also show the potential of such models to identify clusters of users based on their password generation behaviour, which can spot fake profiles and populations more vulnerable to context-aware guesses. The code is publicly available at https://github.com/spring-epfl/DCM_sp

cs.CR↗

arXiv2023

Can Decentralized Learning be more robust than Federated Learning?

Decentralized Learning (DL) is a peer--to--peer learning approach that allows a group of users to jointly train a machine learning model. To ensure correctness, DL should be robust, i.e., Byzantine users must not be able to tamper with the result of the collaboration. In this paper, we introduce two \textit{new} attacks against DL where a Byzantine user can: make the network converge to an arbitrary model of their choice, and exclude an arbitrary user from the learning process. We demonstrate our attacks' efficiency against Self--Centered Clipping, the state--of--the--art robust DL protocol. Finally, we show that the capabilities decentralization grants to Byzantine users result in decentralized learning \emph{always} providing less robustness than federated learning.

cs.LG↗

arXiv2022

Eluding Secure Aggregation in Federated Learning via Model Inconsistency

Secure aggregation is a cryptographic protocol that securely computes the aggregation of its inputs. It is pivotal in keeping model updates private in federated learning. Indeed, the use of secure aggregation prevents the server from learning the value and the source of the individual model updates provided by the users, hampering inference and data attribution attacks. In this work, we show that a malicious server can easily elude secure aggregation as if the latter were not in place. We devise two different attacks capable of inferring information on individual private training datasets, independently of the number of users participating in the secure aggregation. This makes them concrete threats in large-scale, real-world federated learning applications. The attacks are generic and equally effective regardless of the secure aggregation protocol used. They exploit a vulnerability of the federated learning protocol caused by incorrect usage of secure aggregation and lack of parameter validation. Our work demonstrates that current implementations of federated learning with secure aggregation offer only a "false sense of security".

cs.LG↗

arXiv2021

Unleashing the Tiger: Inference Attacks on Split Learning

We investigate the security of Split Learning -- a novel collaborative machine learning framework that enables peak performance by requiring minimal resources consumption. In the present paper, we expose vulnerabilities of the protocol and demonstrate its inherent insecurity by introducing general attack strategies targeting the reconstruction of clients' private training sets. More prominently, we show that a malicious server can actively hijack the learning process of the distributed model and bring it into an insecure state that enables inference attacks on clients' data. We implement different adaptations of the attack and test them on various datasets as well as within realistic threat scenarios. We demonstrate that our attack is able to overcome recently proposed defensive techniques aimed at enhancing the security of the split learning protocol. Finally, we also illustrate the protocol's insecurity against malicious clients by extending previously devised attacks for Federated Learning. To make our results reproducible, we made our code available at https://github.com/pasquini-dario/SplitNN_FSHA.

cs.CR↗

arXiv2021

Interpretable Probabilistic Password Strength Meters via Deep Learning

Probabilistic password strength meters have been proved to be the most accurate tools to measure password strength. Unfortunately, by construction, they are limited to solely produce an opaque security estimation that fails to fully support the user during the password composition. In the present work, we move the first steps towards cracking the intelligibility barrier of this compelling class of meters. We show that probabilistic password meters inherently own the capability of describing the latent relation occurring between password strength and password structure. In our approach, the security contribution of each character composing a password is disentangled and used to provide explicit fine-grained feedback for the user. Furthermore, unlike existing heuristic constructions, our method is free from any human bias, and, more importantly, its feedback has a probabilistic interpretation. In our contribution: (1) we formulate interpretable probabilistic password strength meters; (2) we describe how they can be implemented via an efficient and lightweight deep learning framework suitable for client-side operability.

cs.CR↗

arXiv2021

Reducing Bias in Modeling Real-world Password Strength via Deep Learning and Dynamic Dictionaries

Password security hinges on an in-depth understanding of the techniques adopted by attackers. Unfortunately, real-world adversaries resort to pragmatic guessing strategies such as dictionary attacks that are inherently difficult to model in password security studies. In order to be representative of the actual threat, dictionary attacks must be thoughtfully configured and tuned. However, this process requires a domain-knowledge and expertise that cannot be easily replicated. The consequence of inaccurately calibrating dictionary attacks is the unreliability of password security analyses, impaired by a severe measurement bias. In the present work, we introduce a new generation of dictionary attacks that is consistently more resilient to inadequate configurations. Requiring no supervision or domain-knowledge, this technique automatically approximates the advanced guessing strategies adopted by real-world attackers. To achieve this: (1) We use deep neural networks to model the proficiency of adversaries in building attack configurations. (2) Then, we introduce dynamic guessing strategies within dictionary attacks. These mimic experts' ability to adapt their guessing strategies on the fly by incorporating knowledge on their targets. Our techniques enable more robust and sound password strength estimates within dictionary attacks, eventually reducing overestimation in modeling real-world threats in password security. Code available: https://github.com/TheAdamProject/adams

cs.CR↗

arXiv2020

Improving Password Guessing via Representation Learning

Learning useful representations from unstructured data is one of the core challenges, as well as a driving force, of modern data-driven approaches. Deep learning has demonstrated the broad advantages of learning and harnessing such representations. In this paper, we introduce a deep generative model representation learning approach for password guessing. We show that an abstract password representation naturally offers compelling and versatile properties that can be used to open new directions in the extensively studied, and yet presently active, password guessing field. These properties can establish novel password generation techniques that are neither feasible nor practical with the existing probabilistic and non-probabilistic approaches. Based on these properties, we introduce:(1) A general framework for conditional password guessing that can generate passwords with arbitrary biases; and (2) an Expectation Maximization-inspired framework that can dynamically adapt the estimated password distribution to match the distribution of the attacked password set.

cs.CR↗

arXiv2019

Adversarial Out-domain Examples for Generative Models

Deep generative models are rapidly becoming a common tool for researchers and developers. However, as exhaustively shown for the family of discriminative models, the test-time inference of deep neural networks cannot be fully controlled and erroneous behaviors can be induced by an attacker. In the present work, we show how a malicious user can force a pre-trained generator to reproduce arbitrary data instances by feeding it suitable adversarial inputs. Moreover, we show that these adversarial latent vectors can be shaped so as to be statistically indistinguishable from the set of genuine inputs. The proposed attack technique is evaluated with respect to various GAN images generators using different architectures, training processes and for both conditional and not-conditional setups.

cs.LG↗

arXiv2018

AMG based on compatible weighted matching for GPUs

We describe main issues and design principles of an efficient implementation, tailored to recent generations of Nvidia Graphics Processing Units (GPUs), of an Algebraic Multigrid (AMG) preconditioner previously proposed by one of the authors and already available in the open-source package BootCMatch: Bootstrap algebraic multigrid based on Compatible weighted Matching for standard CPU. The AMG method relies on a new approach for coarsening sparse symmetric positive definite (spd) matrices, named "coarsening based on compatible weighted matching". It exploits maximum weight matching in the adjacency graph of the sparse matrix, driven by the principle of compatible relaxation, providing a suitable aggregation of unknowns which goes beyond the limits of the usual heuristics applied in the current methods. We adopt an approximate solution of the maximum weight matching problem, based on a recently proposed parallel algorithm, referred as the Suitor algorithm, and show that it allow us to obtain good quality coarse matrices for our AMG on GPUs. We exploit inherent parallelism of modern GPUs in all the kernels involving sparse matrix computations both for the setup of the preconditioner and for its application in a Krylov solver, outperforming preconditioners available in Nvidia AmgX library. We report results about a large set of linear systems arising from discretization of scalar and vector partial differential equations (PDEs).

math.NA↗