Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security

Large Language Models LLMs are increasingly vulnerable to adversarial prompts that exploit semantic ambiguities to bypass safety mechanisms, resulting in harmful or inappropriate outputs. Such attacks, including jailbreaking and prompt injection, pose significant risks to the integrity and...

LiteShield: Hybrid Feature Selection-Driven Lightweight Intrusion Detection for Resource-Constrained IoT Networks

The rapid expansion of Internet of Things IoT deployments has enlarged the attack surface of modern digital infrastructure while exposing a key security mismatch: many intrusion detection systems IDSs remain too computationally expensive for constrained IoT environments. This paper presents...

SDNGuardStack: An Explainable Ensemble Learning Framework for High-Accuracy Intrusion Detection in Software-Defined Networks

Software-Defined Networking SDN is another technology that has been developing in the last few years as a relevant technique to improve network programmability and administration. Nonetheless, its centralized design presents a major security issue, which requires effective intrusion detection...

Information-Theoretic Estimation of the Risk of Privacy Leaks

Recent work\citeLiu2016 has shown that dependencies between items in a dataset can lead to privacy leaks. We extend this concept to privacy-preserving transformations, considering a broader set of dependencies captured by correlation metrics. Specifically, we measure the correlation between the...

Learning Obfuscations of LLM Embedding Sequences: Stained Glass Transform

The high cost of ownership of AI compute infrastructure and challenges of robust serving of large language models LLMs has led to a surge in managed Model-as-a-service deployments. Even when enterprises choose on-premises deployments, the compute infrastructure is typically shared across many tea...

PoSyn: Secure Power Side-Channel Aware Synthesis

Power Side-Channel PSC attacks exploit power consumption patterns to extract sensitive information, posing risks to cryptographic operations crucial for secure systems. Traditional countermeasures, such as masking, face challenges including complex integration during synthesis, substantial area...

FERRET: Private Deep Learning Faster and Better Than DPSGD

We revisit 1-bit gradient compression through the lens of mutual-information differential privacy MI-DP. Building on signSGD, we propose FERRET--Fast and Effective Restricted Release for Ethical Training--which transmits at most one sign bit per parameter group with Bernoulli masking. Theory: We...

Streamlining HTTP Flooding Attack Detection through Incremental Feature Selection

Applications over the Web primarily rely on the HTTP protocol to transmit web pages to and from systems. There are a variety of application layer protocols, but among all, HTTP is the most targeted because of its versatility and ease of integration with online services. The attackers leverage the...

Mutual Information Minimization for Side-Channel Attack Resistance Via Optimal Noise Injection

Side-channel attacks SCAs pose a serious threat to system security by extracting secret keys through physical leakages such as power consumption, timing variations, and electromagnetic emissions. Among existing countermeasures, artificial noise injection is recognized as one of the most effective...