Now You (Still) See Me: Detecting Evasive Steganographic Payloads in LLMs

Large language models can be fine-tuned to encode prompt-borne secrets into fluent, seemingly benign outputs. This creates a steganographic exfiltration risk that is difficult to detect with output-level steganalysis. Recent work proposes mechanistic detection using linear probes that recover the...

Information Theoretic Adversarial Training of Large Language Models

Large language models LLMs remain vulnerable to adversarial prompting despite advances in alignment and safety, often exhibiting harmful behaviors under novel attack strategies. While adversarial training can improve robustness, existing approaches are computationally expensive and difficult to...

Sensing Security in Near-Field ISAC: Exploiting Scatterers for Eavesdropper Deception

In this paper, we explore sensing security in near-field NF integrated sensing and communication ISAC scenarios by exploiting known scatterers in the sensing scene. We propose a location deception LD scheme where scatterers are deliberately illuminated with probing power that is higher than that...

Secure Authentication Via Quantum Physical Unclonable Functions: a Review

Quantum Physical Unclonable Functions QPUFs offer a physically grounded approach to secure authentication, extending the capabilities of classical PUFs. This review covers their theoretical foundations and key implementation challenges - such as quantum memories and Haar-randomness -, and...

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...

Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?

Low rank adaptation LoRA has emerged as a prominent technique for fine-tuning large language models LLMs thanks to its superb efficiency gains over previous methods. While extensive studies have examined the performance and structural properties of LoRA, its behavior upon training-time attacks...

Federated One-Shot Learning with Data Privacy and Objective-Hiding

Privacy in federated learning is crucial, encompassing two key aspects: safeguarding the privacy of clients' data and maintaining the privacy of the federator's objective from the clients. While the first aspect has been extensively studied, the second has received much less attention. We present...

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...

AI and Lossy Bottlenecks

Artificial intelligence is poised to upend much of society, removing human limitations inherent in many systems. One such limitation is information and logistical bottlenecks in decision-making. Traditionally, people have been forced to reduce complex choices to a small handful of options that do...

psychedelic-information-theory.com XSS vulnerability

Open Bug Bounty ID: OBB-616199 Description| Value ---|--- Affected Website:| psychedelic-information-theory.com Open Bug Bounty Program:| Create your bounty program now. It's open and free. Vulnerable Application:| Custom Code Vulnerability Type:| XSS Cross Site Scripting / CWE-79 CVSSv3 Score:|...

psychedelic-information-theory.com XSS vulnerability

Open Bug Bounty ID: OBB-550828 Description| Value ---|--- Affected Website:| psychedelic-information-theory.com Open Bug Bounty Program:| Create your bounty program now. It's open and free. Vulnerable Application:| Custom Code Vulnerability Type:| XSS Cross Site Scripting / CWE-79 CVSSv3 Score:|...

Cracking Cryptography and Encryption Exponentially Easier

It’s been a brutal month for crypto. Starting with the Black Hat conference, researchers, engineers and hackers have been unveiling new weaknesses and attacks in different cryptographic implementations that threaten the security of communication and commerce on the Web. Not only have holes been...