Aggregator

The post Upgraded Custom ASPM Dashboards: Build Security Views That Match How Your Teams Work appeared first on Security Boulevard.

The research underscores how AI tools have matured in their cyber offensive capabilities, even as it doesn’t reveal novel or paradigm shifting uses of the technology.

The post Google finds state-sponsored hackers use AI at ‘all stages’ of attack cycle  appeared first on CyberScoop.

AI regulation doesn’t have to be romanticized or feared. Understand what matters in AI governance, compliance, and SaaS risk management.

The post Roses Are Red, AI Is Wild: A Guide to AI Regulation appeared first on Security Boulevard.

In my previous post, I walked through how disconnected MCP servers and AI agents create a growing blind spot in enterprise identity. The problem: thousands of MCP deployments running with overly broad tokens, no authentication, and no connection to your identity fabric. The solution: federate everything through the Maverics AI Identity Gateway. That post assumed...

The post The Agentic Virus: How AI Agents Become Self-Spreading Malware appeared first on Strata.io.

The post The Agentic Virus: How AI Agents Become Self-Spreading Malware appeared first on Security Boulevard.

Session 12B: Malware

Authors, Creators & Presenters: Dung Thuy Nguyen (Vanderbilt University), Ngoc N. Tran (Vanderbilt University), Taylor T. Johnson (Vanderbilt University), Kevin Leach (Vanderbilt University)

PAPER
PBP: Post-Training Backdoor Purification for Malware Classifiers

In recent years, the rise of machine learning (ML) in cybersecurity has brought new challenges, including the increasing threat of backdoor poisoning attacks on ML malware classifiers. These attacks aim to manipulate model behavior when provided with a particular input trigger. For instance, adversaries could inject malicious samples into public malware repositories, contaminating the training data and potentially misclassifying malware by the ML model. Current countermeasures predominantly focus on detecting poisoned samples by leveraging disagreements within the outputs of a diverse set of ensemble models on training data points. However, these methods are not applicable in scenarios involving ML-as-a-Service (MLaaS) or for users who seek to purify a backdoored model post-training. Addressing this scenario, we introduce PBP, a post-training defense for malware classifiers that mitigates various types of backdoor embeddings without assuming any specific backdoor embedding mechanism. Our method exploits the influence of backdoor attacks on the activation distribution of neural networks, independent of the trigger-embedding method. In the presence of a backdoor attack, the activation distribution of each layer is distorted into a mixture of distributions. By regulating the statistics of the batch normalization layers, we can guide a backdoored model to perform similarly to a clean one. Our method demonstrates substantial advantages over several state-of-the-art methods, as evidenced by experiments on two datasets, two types of backdoor methods, and various attack configurations. Our experiments showcase that PBP can mitigate even the SOTA backdoor attacks for malware classifiers, e.g., Jigsaw Puzzle, which was previously demonstrated to be stealthy against existing backdoor defenses. Notably, your approach requires only a small portion of the training data -- only 1% -- to purify the backdoor and reduce the attack success rate from 100% to almost 0%, a 100-fold improvement over the baseline methods.

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 – PBP: Post-Training Backdoor Purification For Malware Classifiers appeared first on Security Boulevard.

You must login to view this content