相关论文: A Modular Approach to Automatic Cyber Threat Attri…

In the real world, agents often have to operate in situations with incomplete information, limited sensing capabilities, and inherently stochastic environments, making individual observations incomplete and unreliable. Moreover, in many…

Proving correctness of distributed or concurrent algorithms is a mind-challenging and complex process. Slight errors in the reasoning are difficult to find, calling for computer-checked proof systems. In order to build computer-checked…

With the growing deployment of sequential recommender systems in e-commerce and other fields, their black-box interfaces raise security concerns: models are vulnerable to extraction and subsequent adversarial manipulation. Existing…

To defend against Advanced Persistent Threats on the endpoint, threat hunting employs security knowledge such as cyber threat intelligence to continuously analyze system audit logs through retrospective scanning, querying, or pattern…

In this paper, we deal with risk evaluation and risk-averse optimization of complex distributed systems with general risk functionals. We postulate a novel set of axioms for the functionals evaluating the total risk of the system. We derive…

Cybersecurity threats are becoming increasingly sophisticated, making traditional defense mechanisms and manual red teaming approaches insufficient for modern organizations. While red teaming has long been recognized as an effective method…

Neural collaborative filtering is the state of art field in the recommender systems area; it provides some models that obtain accurate predictions and recommendations. These models are regression-based, and they just return rating…

Data poisoning attacks aim at manipulating model behaviors through distorting training data. Previously, an aggregation-based certified defense, Deep Partition Aggregation (DPA), was proposed to mitigate this threat. DPA predicts through an…

Prompt injection has emerged as a serious security threat to large language models (LLMs). At present, the current best-practice for defending against newly-discovered prompt injection techniques is to add additional guardrails to the…

The collaborative nature of federated learning (FL) poses a major threat in the form of manipulation of local training data and local updates, known as the Byzantine poisoning attack. To address this issue, many Byzantine-robust aggregation…

Backdoor attacks are a significant threat to large language models (LLMs), often embedded via public checkpoints, yet existing defenses rely on impractical assumptions about trigger settings. To address this challenge, we propose…

Open, unclassified research on secure autonomy is constrained by limited access to operational platforms, contested communications infrastructure, and representative adversarial test conditions. This paper presents a threat-oriented digital…

We present an online voting architecture based on partitioning the election in small clusters of voters and using a new Multi-party Computation algorithm for obtaining voting results from the clusters. This new algorithm has some practical…

This paper proposes a group deliberation oriented multi-agent conversational model to address the limitations of single large language models in complex reasoning tasks. The model adopts a three-level role division architecture consisting…

The incremental diffusion of machine learning algorithms in supporting cybersecurity is creating novel defensive opportunities but also new types of risks. Multiple researches have shown that machine learning methods are vulnerable to…

Advanced Persistent Threats (APTs) are prolonged, stealthy intrusions by skilled adversaries that compromise high-value systems to steal data or disrupt operations. Reconstructing complete attack chains from massive, heterogeneous logs is…

Over-the-air federated learning (OTA-FL) improves communication efficiency by exploiting the superposition property of wireless channels, but this same property also creates a critical security vulnerability: the parameter server (PS)…

Motivated by undetectable risks in generative AI, we study a general robust aggregation problem: how to aggregate several probability distributions to boost safety. We present consensus sampling, a black-box algorithm that, given k…

Rank aggregation with pairwise comparisons is widely encountered in sociology, politics, economics, psychology, sports, etc . Given the enormous social impact and the consequent incentives, the potential adversary has a strong motivation to…

Many transfer problems require re-using previously optimal decisions for solving new tasks, which suggests the need for learning algorithms that can modify the mechanisms for choosing certain actions independently of those for choosing…