Abstract. Sanitizable signature schemes, as defined by Ateniese et al. (ESORICS 2005), allow a signer to partly delegate signing rights to another party, called the sanitizer. That is, the sanitizer is able to modify a predetermined part of the original message such that the integrity and authenticity of the unchanged part is still verifiable. Ateniese et al. identify five security requirements for such schemes (unforgeability, immutability, privacy, transparency and accountability) but do not provide formal specifications for these properties. They also present a scheme that is supposed to satisfy these requirements.Here we revisit the security requirements for sanitizable signatures and, for the first time, present a comprehensive formal treatment. Besides a full characterization of the requirements we also investigate the relationship of the properties, showing for example that unforgeability follows from accountability. We then provide a full security proof for a modification of the original scheme according to our model.

No abstract

Abstract. Sanitizable signatures allow a designated party, called the sanitizer, to modify parts of signed data such that the immutable parts can still be verified with respect to the original signer. Ateniese et al. (ES-ORICS 2005) discuss five security properties for such signature schemes: unforgeability, immutability, privacy, transparency and accountability. These notions have been formalized in a recent work by Brzuska et al. (PKC 2009), discussing also the relationships among the security notions. In addition, they prove a modification of the scheme of Ateniese et al. to be secure according to these notions.Here we discuss that a sixth property of sanitizable signature schemes may be desirable: unlinkability. Basically, this property prevents that one can link sanitized message-signature pairs of the same document, thus allowing to deduce combined information about the original document. We show that this notion implies privacy, the inability to recover the original data of sanitized parts, but is not implied by any of the other five notions. We also discuss a scheme based on group signatures meeting all six security properties.

No abstract

Abstract. We investigate the possibility to prove security of the wellknown blind signature schemes by Chaum, and by Pointcheval and Stern in the standard model, i.e., without random oracles. We subsume these schemes under a more general class of blind signature schemes and show that finding security proofs for these schemes via black-box reductions in the standard model is hard. Technically, our result deploys metareduction techniques showing that black-box reductions for such schemes could be turned into efficient solvers for hard non-interactive cryptographic problems like RSA or discrete-log. Our approach yields significantly stronger impossibility results than previous meta-reductions in other settings by playing off the two security requirements of the blind signatures (unforgeability and blindness).