Tootfinder

InfoFlood: Jailbreaking Large Language Models with Information Overload
Advait Yadav, Haibo Jin, Man Luo, Jun Zhuang, Haohan Wang
https://arxiv.org/abs/2506.12274

InfoFlood: Jailbreaking Large Language Models with Information Overload
Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains. However, their potential to generate harmful responses has raised significant societal and regulatory concerns, especially when manipulated by adversarial techniques known as "jailbreak" attacks. Existing jailbreak methods typically involve appending carefully crafted prefixes or suffixes to malicious prompts in order to bypass the built-in safety mechanisms of these models. In this work, we identif…

A Family of Sequences Generalizing the Thue Morse and Rudin Shapiro Sequences
Russell Jay Hendel
https://arxiv.org/abs/2505.20547 https://

A Family of Sequences Generalizing the Thue Morse and Rudin Shapiro Sequences
For $m \ge 1,$ let $P_m =1^m,$ the binary string of $m$ ones. Further define the infinite sequence $s_m$ by $s_{m,n} = 1$ iff the number of (possibly overlapping) occurrences of $P_m$ in the binary representation of $n$ is odd, $n \ge 0.$ For $m=1,2$ respectively $s_m$ is the Thue-Morse and Rudin-Shapiro sequences. This paper shows: (i) $s_m$ is automatic; (ii) the minimal, DFA (deterministic finite automata) accepting $s_m$ has $2m$ states; (iii) it suffices to use prefixes of length $2^{m-1}$…