Aggregator

Could the Innovation in Non-Human Identities Be the Key to Enhanced Secrets Security? Where progressively leaning towards automation and digital transformation, how can we ensure that the creation and management of Non-Human Identities (NHIs) maintain robust security and compliance? Machine identities, better known as NHIs, are becoming pivotal in cybersecurity solutions across various industries, including […]

The post How does innovation in NHIs contribute to better secrets security? appeared first on Entro.

The post How does innovation in NHIs contribute to better secrets security? appeared first on Security Boulevard.

How Can Non-Human Identities Reshape Cybersecurity in Crisis Management? Have you ever considered the hidden guardians of digital infrastructure? These are the often overlooked Non-Human Identities (NHIs), which are pivotal in managing cybersecurity threats across various industries. Understanding NHIs and their significance is imperative within the context of crisis management strategies, especially when organizations increasingly […]

The post Why does Agentic AI provide a calm approach to crisis management? appeared first on Entro.

The post Why does Agentic AI provide a calm approach to crisis management? appeared first on Security Boulevard.

The Importance of Managing Non-Human Identities in Cloud Security What’s the real cost of neglecting Non-Human Identities (NHIs) in your cybersecurity strategy? When organizations increasingly move to the cloud, understanding and managing NHIs is crucial to ensuring robust, comprehensive security. NHIs, primarily comprised of machine identities, use encrypted secrets like passwords, tokens, or keys to […]

The post How adaptable are Agentic AI systems to evolving cyber threats? appeared first on Entro.

The post How adaptable are Agentic AI systems to evolving cyber threats? appeared first on Security Boulevard.

Why is Managing Non-Human Identities Essential for Cybersecurity? Have you ever wondered how secure your cloud environment truly is in interconnected digital? When organizations increasingly migrate their operations to the cloud, the management of Non-Human Identities (NHIs) and Secrets Security Management becomes more critical. These elements are pivotal for closing the security gaps that can […]

The post How are stakeholders reassured by enhanced secrets scanning methodologies? appeared first on Entro.

The post How are stakeholders reassured by enhanced secrets scanning methodologies? appeared first on Security Boulevard.

You must login to view this content

Session 12C: Membership Inference

Authors, Creators & Presenters: Xinqian Wang (RMIT University), Xiaoning Liu (RMIT University), Shangqi Lai (CSIRO Data61), Xun Yi (RMIT University), Xingliang Yuan (University of Melbourne)

PAPER
SIGuard: Guarding Secure Inference with Post Data Privacy

Secure inference is designed to enable encrypted machine learning model prediction over encrypted data. It will ease privacy concerns when models are deployed in Machine Learning as a Service (MLaaS). For efficiency, most of recent secure inference protocols are constructed using secure multi-party computation (MPC) techniques. They can ensure that MLaaS computes inference without knowing the inputs of users and model owners. However, MPC-based protocols do not hide information revealed from their output. In the context of secure inference, prediction outputs (i.e., inference results of encrypted user inputs) are revealed to the users. As a result, adversaries can compromise output privacy of secure inference, i.e., launching Membership Inference Attacks (MIAs) by querying encrypted models, just like MIAs in plaintext inference. We observe that MPC-based secure inference often yields perturbed predictions due to approximations of nonlinear functions like softmax compared to its plaintext version on identical user inputs. Thus, we evaluate whether or not MIAs can still exploit such perturbed predictions on known secure inference protocols. Our results show that secure inference remains vulnerable to MIAs. The adversary can steal membership information with high successful rates comparable to plaintext MIAs. To tackle this open challenge, we propose SIGuard, a framework to guard the output privacy of secure inference from being exploited by MIAs. SIGuard's protocol can seamlessly be integrated into existing MPC-based secure inference protocols without intruding on their computation. It proceeds with encrypted predictions outputted from secure inference, and then crafts noise for perturbing encrypted predictions without compromising inference accuracy; only the perturbed predictions are revealed to users at the end of protocol execution. SIGuard achieves stringent privacy guarantees via a co-design of MPC techniques and machine learning. We further conduct comprehensive evaluations to find the optimal hyper-parameters for balanced efficiency and defense effectiveness against MIAs. Together, our evaluation shows SIGuard effectively defends against MIAs by reducing the attack accuracy to be around the random guess with overhead (1.1s), occupying ~24.8% of secure inference (3.29s) on widely used ResNet34 over CIFAR-10.

ABOUT NDSS
The Network and Distributed System Security Symposium (NDSS) fosters information exchange among researchers and practitioners of network and distributed system security. The target audience includes those interested in practical aspects of network and distributed system security, with a focus on actual system design and implementation. A major goal is to encourage and enable the Internet community to apply, deploy, and advance the state of available security technologies.

Our thanks to the Network and Distributed System Security (NDSS) Symposium for publishing their Creators, Authors and Presenter’s superb NDSS Symposium 2025 Conference content on the Organizations' YouTube Channel.

Permalink

The post NDSS 2025 – SiGuard: Guarding Secure Inference With Post Data Privacy appeared first on Security Boulevard.

In many law firms today, leadership believes their data is secure. Policies are documented, annual reviews are completed, and vendor questionnaires are answered with confidence. On paper, the safeguards look strong.

Related: The cost of law firm breaches

Yet in … (more…)

The post GUEST ESSAY: The hidden risks lurking beneath legal AI — permission sprawl, governance drift first appeared on The Last Watchdog.

The post GUEST ESSAY: The hidden risks lurking beneath legal AI — permission sprawl, governance drift appeared first on Security Boulevard.

You must login to view this content

You must login to view this content

You must login to view this content