The Price of Pessimism for Automated Defense

• URL: http://arxiv.org/abs/2409.19237v1
• Date: Sat, 28 Sep 2024 04:54:23 GMT
• Title: The Price of Pessimism for Automated Defense
• Authors: Erick Galinkin, Emmanouil Pountourakis, Spiros Mancoridis,
• Abstract summary: We demonstrate that preparing for the worst case rather than the most probable case may yield suboptimal outcomes for learning agents. By considering different models of attacker knowledge about the state of the game and a defender's hidden information, we find that there is a cost to the defender for optimizing against the worst case.
• Score: 0.06599842398809413
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The well-worn George Box aphorism ``all models are wrong, but some are useful'' is particularly salient in the cybersecurity domain, where the assumptions built into a model can have substantial financial or even national security impacts. Computer scientists are often asked to optimize for worst-case outcomes, and since security is largely focused on risk mitigation, preparing for the worst-case scenario appears rational. In this work, we demonstrate that preparing for the worst case rather than the most probable case may yield suboptimal outcomes for learning agents. Through the lens of stochastic Bayesian games, we first explore different attacker knowledge modeling assumptions that impact the usefulness of models to cybersecurity practitioners. By considering different models of attacker knowledge about the state of the game and a defender's hidden information, we find that there is a cost to the defender for optimizing against the worst case.

Related papers

• PropensityBench: Evaluating Latent Safety Risks in Large Language Models via an Agentic Approach [49.14349403242654]
  We present $textbfPropensityBench$, a novel benchmark framework that assesses the proclivity of models to engage in risky behaviors.<n>Our framework includes 5,874 scenarios with 6,648 tools spanning four high-risk domains: cybersecurity, self-proliferation, biosecurity, and chemical security.<n>Across open-source and proprietary frontier models, we uncover 9 alarming signs of propensity: models frequently choose high-risk tools when under pressure.
  arXiv  Detail & Related papers  (2025-11-24T18:46:44Z)
• MISLEADER: Defending against Model Extraction with Ensembles of Distilled Models [56.09354775405601]
  Model extraction attacks aim to replicate the functionality of a black-box model through query access.<n>Most existing defenses presume that attacker queries have out-of-distribution (OOD) samples, enabling them to detect and disrupt suspicious inputs.<n>We propose MISLEADER, a novel defense strategy that does not rely on OOD assumptions.
  arXiv  Detail & Related papers  (2025-06-03T01:37:09Z)
• PsybORG+: Modeling and Simulation for Detecting Cognitive Biases in Advanced Persistent Threats [10.161416622040722]
  This work introduces PsybORG$+$, a multi-agent cybersecurity simulation environment designed to model APT behaviors influenced by cognitive vulnerabilities. A classification model is built for cognitive vulnerability inference and a simulator is designed for synthetic data generation. Results show that PsybORG$+$ can effectively model APT attackers with different loss aversion and confirmation bias levels.
  arXiv  Detail & Related papers  (2024-08-02T15:00:58Z)
• Learn to Disguise: Avoid Refusal Responses in LLM's Defense via a Multi-agent Attacker-Disguiser Game [28.33029508522531]
  Malicious attackers induce large models to jailbreak and generate information containing illegal, privacy-invasive information. Large models counter malicious attackers' attacks using techniques such as safety alignment. We propose a multi-agent attacker-disguiser game approach to achieve a weak defense mechanism that allows the large model to both safely reply to the attacker and hide the defense intent.
  arXiv  Detail & Related papers  (2024-04-03T07:43:11Z)
• Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models [112.48136829374741]
  In this paper, we unveil a new vulnerability: the privacy backdoor attack. When a victim fine-tunes a backdoored model, their training data will be leaked at a significantly higher rate than if they had fine-tuned a typical model. Our findings highlight a critical privacy concern within the machine learning community and call for a reevaluation of safety protocols in the use of open-source pre-trained models.
  arXiv  Detail & Related papers  (2024-04-01T16:50:54Z)
• PROSAC: Provably Safe Certification for Machine Learning Models under Adversarial Attacks [20.73708921078335]
  State-of-the-art machine learning models can be seriously compromised by adversarial perturbations. We propose a new approach to certify the performance of machine learning models in the presence of adversarial attacks.
  arXiv  Detail & Related papers  (2024-02-04T22:45:20Z)
• Towards more Practical Threat Models in Artificial Intelligence Security [66.67624011455423]
  Recent works have identified a gap between research and practice in artificial intelligence security. We revisit the threat models of the six most studied attacks in AI security research and match them to AI usage in practice.
  arXiv  Detail & Related papers  (2023-11-16T16:09:44Z)
• Designing an attack-defense game: how to increase robustness of financial transaction models via a competition [69.08339915577206]
  Given the escalating risks of malicious attacks in the finance sector, understanding adversarial strategies and robust defense mechanisms for machine learning models is critical. We aim to investigate the current state and dynamics of adversarial attacks and defenses for neural network models that use sequential financial data as the input. We have designed a competition that allows realistic and detailed investigation of problems in modern financial transaction data. The participants compete directly against each other, so possible attacks and defenses are examined in close-to-real-life conditions.
  arXiv  Detail & Related papers  (2023-08-22T12:53:09Z)
• Isolation and Induction: Training Robust Deep Neural Networks against Model Stealing Attacks [51.51023951695014]
  Existing model stealing defenses add deceptive perturbations to the victim's posterior probabilities to mislead the attackers. This paper proposes Isolation and Induction (InI), a novel and effective training framework for model stealing defenses. In contrast to adding perturbations over model predictions that harm the benign accuracy, we train models to produce uninformative outputs against stealing queries.
  arXiv  Detail & Related papers  (2023-08-02T05:54:01Z)
• Avoid Adversarial Adaption in Federated Learning by Multi-Metric Investigations [55.2480439325792]
  Federated Learning (FL) facilitates decentralized machine learning model training, preserving data privacy, lowering communication costs, and boosting model performance through diversified data sources. FL faces vulnerabilities such as poisoning attacks, undermining model integrity with both untargeted performance degradation and targeted backdoor attacks. We define a new notion of strong adaptive adversaries, capable of adapting to multiple objectives simultaneously. MESAS is the first defense robust against strong adaptive adversaries, effective in real-world data scenarios, with an average overhead of just 24.37 seconds.
  arXiv  Detail & Related papers  (2023-06-06T11:44:42Z)
• Learning to Defend by Attacking (and Vice-Versa): Transfer of Learning in Cybersecurity Games [1.14219428942199]
  We present a novel model of human decision-making inspired by the cognitive faculties of Instance-Based Learning Theory, Theory of Mind, and Transfer of Learning. This model functions by learning from both roles in a security scenario: defender and attacker, and by making predictions of the opponent's beliefs, intentions, and actions. Results from simulation experiments demonstrate the potential usefulness of cognitively inspired models of agents trained in attack and defense roles.
  arXiv  Detail & Related papers  (2023-06-03T17:51:04Z)
• Careful What You Wish For: on the Extraction of Adversarially Trained Models [2.707154152696381]
  Recent attacks on Machine Learning (ML) models pose several security and privacy threats. We propose a framework to assess extraction attacks on adversarially trained models. We show that adversarially trained models are more vulnerable to extraction attacks than models obtained under natural training circumstances.
  arXiv  Detail & Related papers  (2022-07-21T16:04:37Z)
• A Framework for Understanding Model Extraction Attack and Defense [48.421636548746704]
  We study tradeoffs between model utility from a benign user's view and privacy from an adversary's view. We develop new metrics to quantify such tradeoffs, analyze their theoretical properties, and develop an optimization problem to understand the optimal adversarial attack and defense strategies.
  arXiv  Detail & Related papers  (2022-06-23T05:24:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.